--- title: "R Notebook" output: html_notebook --- #### Packages ```{r} install.packages("dplyr") library(dplyr) install.packages("stargazer") library(stargazer) install.packages("haven") library(haven) CMPS_2020_Youth_sample_weighted_SPSS <- CMPS_2020_Youth_sample_weighted_SPSS |> haven::zap_labels() ``` #### Variables for Personally Having DACA ```{r} #### DACA Adults CMPS_2020_primary_sample_weighted <- CMPS_2020_primary_sample_weighted %>% mutate(daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, # answered yes to DACA use AND selected "Me" Q470 == 2 ~ 0, # never used DACA program Q470 == 1 & Q471r1 != 1 ~ 0, # used DACA but not personally TRUE ~ NA_real_ # catches any missing/ambiguous responses )) #### DACA Youth CMPS_2020_Youth_sample_weighted_SPSS <- CMPS_2020_Youth_sample_weighted_SPSS %>% mutate(daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, # answered yes to DACA use AND selected "Me" Q470 == 2 ~ 0, # never used DACA program Q470 == 1 & Q471r1 != 1 ~ 0, # used DACA but not personally TRUE ~ NA_real_ # catches any missing/ambiguous responses )) ##### Creating daca variables exclusive to Latinos #### DACA Adults Latino CMPS.Latino.Adult <- CMPS.Latino.Adult %>% mutate(daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, # answered yes to DACA use AND selected "Me" Q470 == 2 ~ 0, # never used DACA program Q470 == 1 & Q471r1 != 1 ~ 0, # used DACA but not personally TRUE ~ NA_real_ # catches any missing/ambiguous responses )) xtabs(~ daca_personal + Age, data = CMPS.Latino.Adult) #### DACA Youth CMPS_2020_Youth_sample_weighted_SPSS <- CMPS_2020_Youth_sample_weighted_SPSS %>% mutate(daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, # answered yes to DACA use AND selected "Me" Q470 == 2 ~ 0, # never used DACA program Q470 == 1 & Q471r1 != 1 ~ 0, # used DACA but not personally TRUE ~ NA_real_ # catches any missing/ambiguous responses )) ``` #################################################################################################### #################################################################################################### ################################################### Re-Coding Youth Data ########################### #################################################################################################### #################################################################################################### ##### American Identity ```{r} #### Reverse Coding Priority of American Identity CMPS_2020_Youth_sample_weighted_SPSS$American.Identity <- NA CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 1] <- 8 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 2] <- 7 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 3] <- 6 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 4] <- 5 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 5] <- 4 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 6] <- 3 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 7] <- 2 CMPS_2020_Youth_sample_weighted_SPSS$American.Identity[CMPS_2020_Youth_sample_weighted_SPSS$Q560r8 == 8] <- 1 table(CMPS_2020_Youth_sample_weighted_SPSS$American.Identity) ``` ### Citizenship Status ```{r} ### Citizenship CMPS_2020_Youth_sample_weighted_SPSS$Citizenship <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 6] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 7] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Temporary resident (5 years)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "none"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "N/A)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "illegal immigrant)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Us citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "us citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "US Born Citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "us born citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "not sure)"] <- NA CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "None of the above)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "none of the above)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural US citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural US citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "illegal immigrant)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "i am a citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Born US Citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Born us Citizen)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Born in the US)"] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Citizenship[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 3] <- 1 #### DACA (or similar) CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 3] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 5] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 4] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Temporary resident (5 years)"] <- 1 # DACA Strict CMPS_2020_Youth_sample_weighted_SPSS$DACA.2 <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.2[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 5] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 4] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Temporary resident (5 years)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Us citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "us citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "US Born Citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "us born citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "not sure)"] <- NA CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "None of the above)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "none of the above)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural US citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural US citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "illegal immigrant)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "i am a citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Born US Citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Born us Citizen)"] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$DACA.Temp[CMPS_2020_Youth_sample_weighted_SPSS$Q807r8oe == "Born in the US)"] <- 0 ``` ##### Control Variables ##### ```{r} ### Skin Color table(CMPS_2020_Youth_sample_weighted_SPSS$Q261) CMPS_2020_Youth_sample_weighted_SPSS$SkinColor <- NA CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 2] <- 2 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 3] <- 3 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 4] <- 4 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 5] <- 5 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 6] <- 6 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 7] <- 7 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 8] <- 8 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 9] <- 9 CMPS_2020_Youth_sample_weighted_SPSS$SkinColor[CMPS_2020_Youth_sample_weighted_SPSS$Q261 == 10] <- 10 # Education CMPS_2020_Youth_sample_weighted_SPSS$Education <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Education[CMPS_2020_Youth_sample_weighted_SPSS$S13 == 1] <- 1 # Grade 1-8 CMPS_2020_Youth_sample_weighted_SPSS$Education[CMPS_2020_Youth_sample_weighted_SPSS$S13 == 2] <- 2 # Some HS CMPS_2020_Youth_sample_weighted_SPSS$Education[CMPS_2020_Youth_sample_weighted_SPSS$S13 >= 3] <- 3 # HS or GED CMPS_2020_Youth_sample_weighted_SPSS$Education[CMPS_2020_Youth_sample_weighted_SPSS$S13 >= 4] <- 4 # Some College table(CMPS_2020_Youth_sample_weighted_SPSS$S13) # Type of Community CMPS_2020_Youth_sample_weighted_SPSS$community.type <- 0 CMPS_2020_Youth_sample_weighted_SPSS$community.type[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 5 #large urban CMPS_2020_Youth_sample_weighted_SPSS$community.type[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 4 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$community.type[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 3 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$community.type[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 2 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$community.type[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 1 #rural area # Large Urban Community CMPS_2020_Youth_sample_weighted_SPSS$Large.Urban.Community <-0 CMPS_2020_Youth_sample_weighted_SPSS$Large.Urban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 1 #large urban CMPS_2020_Youth_sample_weighted_SPSS$Large.Urban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 0 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$Large.Urban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 0 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$Large.Urban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 0 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$Large.Urban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 0 #rural area # Suburbs CMPS_2020_Youth_sample_weighted_SPSS$Small.Suburban.Community <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Small.Suburban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 0 #large urban CMPS_2020_Youth_sample_weighted_SPSS$Small.Suburban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 1 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$Small.Suburban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 1 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$Small.Suburban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 0 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$Small.Suburban.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 0 #rural area # Small Town / City / Rural CMPS_2020_Youth_sample_weighted_SPSS$Small.City.Town <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Small.City.Town[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 0 #large urban CMPS_2020_Youth_sample_weighted_SPSS$Small.City.Town[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 0 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$Small.City.Town[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 0 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$Small.City.Town[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 1 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$Small.City.Town[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 1 #rural area # Rural Community CMPS_2020_Youth_sample_weighted_SPSS$Rural.Community <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Rural.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 0 #large urban CMPS_2020_Youth_sample_weighted_SPSS$Rural.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 0 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$Rural.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 0 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$Rural.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 0 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$Rural.Community[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 1 #rural area ### Type of Community Urban vs. Small CMPS_2020_Youth_sample_weighted_SPSS$Community.Large <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Community.Large[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 1 #large urban CMPS_2020_Youth_sample_weighted_SPSS$Community.Large[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 1 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$Community.Large[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 0 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$Community.Large[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 0 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$Community.Large[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 0 #rural area CMPS_2020_Youth_sample_weighted_SPSS$Community.Small <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Community.Small[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 1] <- 0 #large urban CMPS_2020_Youth_sample_weighted_SPSS$Community.Small[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 2] <- 0 #large suburb CMPS_2020_Youth_sample_weighted_SPSS$Community.Small[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 3] <- 1 #small suburb CMPS_2020_Youth_sample_weighted_SPSS$Community.Small[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 4] <- 1 #small town/city CMPS_2020_Youth_sample_weighted_SPSS$Community.Small[CMPS_2020_Youth_sample_weighted_SPSS$Q14 == 5] <- 1 #rural area # How you became interested in politics CMPS_2020_Youth_sample_weighted_SPSS$interest.politics <- 0 CMPS_2020_Youth_sample_weighted_SPSS$interest.politics[CMPS_2020_Youth_sample_weighted_SPSS$Q30 == 1] <- 0 #pres camp CMPS_2020_Youth_sample_weighted_SPSS$interest.politics[CMPS_2020_Youth_sample_weighted_SPSS$Q30 == 2] <- 0 #local camp CMPS_2020_Youth_sample_weighted_SPSS$interest.politics[CMPS_2020_Youth_sample_weighted_SPSS$Q30 == 3] <- 1 #personal exp CMPS_2020_Youth_sample_weighted_SPSS$interest.politics[CMPS_2020_Youth_sample_weighted_SPSS$Q30 == 4] <- 0 #major pol event CMPS_2020_Youth_sample_weighted_SPSS$interest.politics[CMPS_2020_Youth_sample_weighted_SPSS$Q30 == 5] <- 0 #other ## Ideology: When it comes to politics, do you think of yourself as liberal, moderate, or conservative? CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 1] <- 6 # very liberal CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 2] <- 5 # liberal CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 3] <- 4 # moderate CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 4] <- 3 # somewhat conservative CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 5] <- 2 # very conservative CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Liberal[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 6] <- 1 # none of these ### Reject Ideology CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Ideology.Scale.Reject[CMPS_2020_Youth_sample_weighted_SPSS$Q43 == 6] <- 1 # none of these # Gender (female) CMPS_2020_Youth_sample_weighted_SPSS$Gender <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Gender[CMPS_2020_Youth_sample_weighted_SPSS$S3b == 1] <- 0 # Male CMPS_2020_Youth_sample_weighted_SPSS$Gender[CMPS_2020_Youth_sample_weighted_SPSS$S3b == 2] <- 1 # Female CMPS_2020_Youth_sample_weighted_SPSS$Gender[CMPS_2020_Youth_sample_weighted_SPSS$S3b == 3] <- 0 # Non-binary CMPS_2020_Youth_sample_weighted_SPSS$Gender[CMPS_2020_Youth_sample_weighted_SPSS$S3b == 4] <- 0 # Party Identification CMPS_2020_Youth_sample_weighted_SPSS$Party.ID <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1] <- "Republican" CMPS_2020_Youth_sample_weighted_SPSS$Party.ID[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2] <- "Democrat" CMPS_2020_Youth_sample_weighted_SPSS$Party.ID[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 3] <- "Independent" CMPS_2020_Youth_sample_weighted_SPSS$Party.ID[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 4] <- "Other" table(CMPS_2020_Youth_sample_weighted_SPSS$Party.ID) # Party Identification (Democrat) CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 4] <- 0 # Party Identification (Strong Democrat) CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 4] <- 0 # Party Identification (Republican) CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 4] <- 0 table(CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep) # Party Identification (Independent) CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Ind <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Ind[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Ind[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Ind[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 3] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Ind[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 4] <- 0 table(CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Rep) table(CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Dem) table(CMPS_2020_Youth_sample_weighted_SPSS$Party.ID.Ind) ### Point Scale (Democrat) CMPS_2020_Youth_sample_weighted_SPSS$Party.Scale.Dem <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Party.Scale.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1 & CMPS_2020_Youth_sample_weighted_SPSS$Q22 == 2] <- 0 # not strong rep CMPS_2020_Youth_sample_weighted_SPSS$Party.Scale.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1 & CMPS_2020_Youth_sample_weighted_SPSS$Q22 == 1] <- 0 # strong rep CMPS_2020_Youth_sample_weighted_SPSS$Party.Scale.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2 & CMPS_2020_Youth_sample_weighted_SPSS$Q22 == 2] <- 1 # not strong dem CMPS_2020_Youth_sample_weighted_SPSS$Party.Scale.Dem[CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2 & CMPS_2020_Youth_sample_weighted_SPSS$Q22 == 1] <- 2 # strong dem table(CMPS_2020_Youth_sample_weighted_SPSS$Party.Scale.Dem) ### Creating a 7-Point Party Scale Democrats CMPS_2020_Youth_sample_weighted_SPSS <- CMPS_2020_Youth_sample_weighted_SPSS %>% mutate(Democratic.Partisanship.7P = case_when( CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1 & CMPS_2020_Youth_sample_weighted_SPSS$Q22 == 1 ~ 1, # Strong Republican CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2 & CMPS_2020_Youth_sample_weighted_SPSS$Q22 == 1 ~ 7, # Strong Dem CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 1 ~ 2, # Republican CMPS_2020_Youth_sample_weighted_SPSS$Q23 == 1 ~ 3, # Lean Republican CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 3 ~ 4, # Independent CMPS_2020_Youth_sample_weighted_SPSS$Q23 == 3 ~ 4, # Independent CMPS_2020_Youth_sample_weighted_SPSS$Q23 == 2 ~ 5, # Lean Dem CMPS_2020_Youth_sample_weighted_SPSS$Q21 == 2 ~ 6, # Democrat CMPS_2020_Youth_sample_weighted_SPSS$Q23 == 88 ~ NA, # Dont know TRUE ~ NA_integer_ )) ### Language of Survey CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 1] <- 1 # English CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 2] <- 2 # Spanish CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 6] <- 0 ### Language of Survey Spnaish CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 1] <- 0 # English CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 2] <- 1 # Spanish CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Survey.Language.Spanish[CMPS_2020_Youth_sample_weighted_SPSS$S1 == 6] <- 0 ### US Born Parents CMPS_2020_Youth_sample_weighted_SPSS$Parent_US_Born <- NA CMPS_2020_Youth_sample_weighted_SPSS$Parent_US_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Parent_US_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_US_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_US_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_US_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 88] <- NA ### Immigrant Parents CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born <- NA CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 2] <- 2 CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Parent_Foreign_Born[CMPS_2020_Youth_sample_weighted_SPSS$Q809 == 88] <- 0 ### Mothers Education CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu <- NA CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 2] <- 2 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 3] <- 3 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 4] <- 4 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 5] <- 5 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 6] <- 6 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 7] <- 7 CMPS_2020_Youth_sample_weighted_SPSS$Mother_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q804 == 8] <- NA ### Father's Education CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu <- NA CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 2] <- 2 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 3] <- 3 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 4] <- 4 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 5] <- 5 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 6] <- 6 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 7] <- 7 CMPS_2020_Youth_sample_weighted_SPSS$Father_Edu[CMPS_2020_Youth_sample_weighted_SPSS$Q805 == 8] <- NA ### Combining Parents Education CMPS_2020_Youth_sample_weighted_SPSS$Parent_Education <- with( CMPS_2020_Youth_sample_weighted_SPSS, pmax(Mother_Edu, Father_Edu, na.rm = TRUE) ) ``` ## Seperating the Data by Primary Race*** ```{r} # Primary Race Latino CMPS_2020_Youth_sample_weighted_SPSS$Latinx <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 2] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 6] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latinx[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 7] <- 0 # Latino, including white CMPS_2020_Youth_sample_weighted_SPSS$Latino_White <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Latino_White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Racer2 == 1] <-1 CMPS_2020_Youth_sample_weighted_SPSS$Latino_White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Racer2 == 0] <-0 # Primary Race African American CMPS_2020_Youth_sample_weighted_SPSS$AfricanAmerican <- 0 CMPS_2020_Youth_sample_weighted_SPSS$AfricanAmerican[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 3] <- 1 summary(CMPS_2020_Youth_sample_weighted_SPSS$AfricanAmerican) # Primary Race Asian CMPS_2020_Youth_sample_weighted_SPSS$Asian <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 4] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 6] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$Asian[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 7] <- 0 summary(CMPS_2020_Youth_sample_weighted_SPSS$Asian) # Primary Race White CMPS_2020_Youth_sample_weighted_SPSS$White <- 0 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 1] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 6] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$White[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 7] <- 0 summary(CMPS_2020_Youth_sample_weighted_SPSS$White) ## Subset Data Frames by race for Teenagers CMPS.Latino.Teen <- CMPS_2020_Youth_sample_weighted_SPSS[CMPS_2020_Youth_sample_weighted_SPSS$Latinx == "1",] CMPS.Latino.Teen.Citizens <- CMPS.Latino.Teen[CMPS.Latino.Teen$Citizenship == "1",] CMPS.Black.Teen <- CMPS_2020_Youth_sample_weighted_SPSS[CMPS_2020_Youth_sample_weighted_SPSS$AfricanAmerican == "1",] CMPS.White.Teen <- CMPS_2020_Youth_sample_weighted_SPSS[CMPS_2020_Youth_sample_weighted_SPSS$White == "1",] CMPS.White.Latino.Teen <- CMPS_2020_Youth_sample_weighted_SPSS[CMPS_2020_Youth_sample_weighted_SPSS$Latino_White == "1",] CMPS.Asian.Teen <- CMPS_2020_Youth_sample_weighted_SPSS[CMPS_2020_Youth_sample_weighted_SPSS$S2_Race_Prime == 4,] ``` #################################################################################################### #################################################################################################### ################################################### Re-Coding Adult Data ########################### #################################################################################################### #################################################################################################### #### American Identity ```{r} CMPS_2020_primary_sample_weighted$American.Identity <- NA CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 1] <- 8 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 2] <- 7 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 3] <- 6 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 4] <- 5 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 5] <- 4 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 6] <- 3 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 7] <- 2 CMPS_2020_primary_sample_weighted$American.Identity[CMPS_2020_primary_sample_weighted$Q560r8 == 8] <- 1 table(CMPS_2020_primary_sample_weighted$American.Identity) ``` ### Personal Status ```{r} ### Citizenship CMPS_2020_primary_sample_weighted$Citizenship <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 1] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 2] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 3] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 4] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 5] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 6] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 7] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Temporary resident (5 years)"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "none"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "N/A)"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "illegal immigrant)"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Us citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "us citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "US Born Citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "us born citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "not sure)"] <- NA CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "None of the above)"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "none of the above)"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural US citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural US citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "illegal immigrant)"] <- 0 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "i am a citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Born US Citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Born us Citizen)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807r8oe == "Born in the US)"] <- 1 CMPS_2020_primary_sample_weighted$Citizenship[CMPS_2020_primary_sample_weighted$Q807 == 3] <- 1 #### DACA, or similar program CMPS_2020_primary_sample_weighted$DACA.Temp <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807 == 3] <- 1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807 == 5] <- 1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807 == 4] <- 1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Temporary resident (5 years)"] <- 1 ### DACA VS. Citizens and TPS # DACA 2 CMPS_2020_primary_sample_weighted$DACA.2 <- 0 CMPS_2020_primary_sample_weighted$DACA.2[CMPS_2020_primary_sample_weighted$Q807 == 5] <- 1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807 == 4] <- 1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Temporary resident (5 years)"] <- 1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Us citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "us citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "US Born Citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "us born citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "not sure)"] <- NA CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "None of the above)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "none of the above)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural US citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural US citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Natural born citizen, parents were naturalized)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "illegal immigrant)"] <- -1 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "i am a citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Born US Citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Born us Citizen)"] <- 0 CMPS_2020_primary_sample_weighted$DACA.Temp[CMPS_2020_primary_sample_weighted$Q807r8oe == "Born in the US)"] <- 0 ######### Legal Permanent Resident (Youth and Adults). ######### # Adults CMPS_2020_primary_sample_weighted$LPR <- 0 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 1] <- 0 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 2] <- 1 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 3] <- 1 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 4] <- 0 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 5] <- 0 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 6] <- 0 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 7] <- 0 CMPS_2020_primary_sample_weighted$LPR[CMPS_2020_primary_sample_weighted$Q807 == 8] <- NA # Youth CMPS_2020_Youth_sample_weighted_SPSS$LPR <- 0 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 2] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 3] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 4] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 6] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 7] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$LPR[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 8] <- 0 ######### Visa Holders (Youth and Adults) ########## # Adult CMPS_2020_primary_sample_weighted$visa_holder <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 1] <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 2] <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 3] <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 4] <- 1 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 5] <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 6] <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 7] <- 0 CMPS_2020_primary_sample_weighted$visa_holder[CMPS_2020_primary_sample_weighted$Q807 == 8] <- 0 # Youth CMPS_2020_Youth_sample_weighted_SPSS$visa_holder <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 1] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 2] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 3] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 4] <- 1 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 5] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 6] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 7] <- 0 CMPS_2020_Youth_sample_weighted_SPSS$visa_holder[CMPS_2020_Youth_sample_weighted_SPSS$Q807 == 8] <- 0 ``` ##### Control Variables ##### ```{r} ## Skin Color CMPS_2020_primary_sample_weighted$Skin.Color <- NA CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 1] <- 1 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 2] <- 2 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 3] <- 3 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 4] <- 4 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 5] <- 5 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 6] <- 6 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 7] <- 7 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 8] <- 8 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 9] <- 9 CMPS_2020_primary_sample_weighted$Skin.Color[CMPS_2020_primary_sample_weighted$Q261 == 10] <- 10 # Education CMPS_2020_primary_sample_weighted$Education <- 0 CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 == 1] <- 1 # Grade 1-8 CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 == 2] <- 2 # Some HS CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 >= 3] <- 3 # HS or GED CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 >= 4] <- 4 # HS or GED CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 >= 5] <- 5 # HS or GED CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 >= 6] <- 6 # HS or GED CMPS_2020_primary_sample_weighted$Education[CMPS_2020_primary_sample_weighted$S13 >= 7] <- 7 # HS or GED # Type of Community CMPS_2020_primary_sample_weighted$community.type <- 0 CMPS_2020_primary_sample_weighted$community.type[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 5 #large urban CMPS_2020_primary_sample_weighted$community.type[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 4 #large suburb CMPS_2020_primary_sample_weighted$community.type[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 3 #small suburb CMPS_2020_primary_sample_weighted$community.type[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 2 #small town/city CMPS_2020_primary_sample_weighted$community.type[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 1 #rural area # Large Urban Community CMPS_2020_primary_sample_weighted$Large.Urban.Community <-0 CMPS_2020_primary_sample_weighted$Large.Urban.Community[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 1 #large urban CMPS_2020_primary_sample_weighted$Large.Urban.Community[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 0 #large suburb CMPS_2020_primary_sample_weighted$Large.Urban.Community[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 0 #small suburb CMPS_2020_primary_sample_weighted$Large.Urban.Community[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 0 #small town/city CMPS_2020_primary_sample_weighted$Large.Urban.Community[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 0 #rural area # Suburbs CMPS_2020_primary_sample_weighted$Small.Suburban.Community <- 0 CMPS_2020_primary_sample_weighted$Small.Suburban.Community[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 0 #large urban CMPS_2020_primary_sample_weighted$Small.Suburban.Community[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 1 #large suburb CMPS_2020_primary_sample_weighted$Small.Suburban.Community[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 1 #small suburb CMPS_2020_primary_sample_weighted$Small.Suburban.Community[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 0 #small town/city CMPS_2020_primary_sample_weighted$Small.Suburban.Community[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 0 #rural area # Small Town / City / Rural CMPS_2020_primary_sample_weighted$Small.City.Town <- 0 CMPS_2020_primary_sample_weighted$Small.City.Town[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 0 #large urban CMPS_2020_primary_sample_weighted$Small.City.Town[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 0 #large suburb CMPS_2020_primary_sample_weighted$Small.City.Town[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 0 #small suburb CMPS_2020_primary_sample_weighted$Small.City.Town[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 1 #small town/city CMPS_2020_primary_sample_weighted$Small.City.Town[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 1 #rural area # Rural Community CMPS_2020_primary_sample_weighted$Rural.Community <- 0 CMPS_2020_primary_sample_weighted$Rural.Community[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 0 #large urban CMPS_2020_primary_sample_weighted$Rural.Community[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 0 #large suburb CMPS_2020_primary_sample_weighted$Rural.Community[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 0 #small suburb CMPS_2020_primary_sample_weighted$Rural.Community[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 0 #small town/city CMPS_2020_primary_sample_weighted$Rural.Community[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 1 #rural area ### Type of Community Urban vs. Small CMPS_2020_primary_sample_weighted$Community.Large <- 0 CMPS_2020_primary_sample_weighted$Community.Large[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 1 #large urban CMPS_2020_primary_sample_weighted$Community.Large[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 1 #large suburb CMPS_2020_primary_sample_weighted$Community.Large[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 0 #small suburb CMPS_2020_primary_sample_weighted$Community.Large[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 0 #small town/city CMPS_2020_primary_sample_weighted$Community.Large[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 0 #rural area CMPS_2020_primary_sample_weighted$Community.Small <- 0 CMPS_2020_primary_sample_weighted$Community.Small[CMPS_2020_primary_sample_weighted$Q14 == 1] <- 0 #large urban CMPS_2020_primary_sample_weighted$Community.Small[CMPS_2020_primary_sample_weighted$Q14 == 2] <- 0 #large suburb CMPS_2020_primary_sample_weighted$Community.Small[CMPS_2020_primary_sample_weighted$Q14 == 3] <- 1 #small suburb CMPS_2020_primary_sample_weighted$Community.Small[CMPS_2020_primary_sample_weighted$Q14 == 4] <- 1 #small town/city CMPS_2020_primary_sample_weighted$Community.Small[CMPS_2020_primary_sample_weighted$Q14 == 5] <- 1 #rural area # How you became interested in politics CMPS_2020_primary_sample_weighted$interest.politics <- 0 CMPS_2020_primary_sample_weighted$interest.politics[CMPS_2020_primary_sample_weighted$Q30 == 1] <- 0 #pres camp CMPS_2020_primary_sample_weighted$interest.politics[CMPS_2020_primary_sample_weighted$Q30 == 2] <- 0 #local camp CMPS_2020_primary_sample_weighted$interest.politics[CMPS_2020_primary_sample_weighted$Q30 == 3] <- 1 #personal exp CMPS_2020_primary_sample_weighted$interest.politics[CMPS_2020_primary_sample_weighted$Q30 == 4] <- 0 #major pol event CMPS_2020_primary_sample_weighted$interest.politics[CMPS_2020_primary_sample_weighted$Q30 == 5] <- 0 #other ## Ideology: When it comes to politics, do you think of yourself as liberal, moderate, or conservative? CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal[CMPS_2020_primary_sample_weighted$Q43 == 1] <- 6 # very liberal CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal[CMPS_2020_primary_sample_weighted$Q43 == 2] <- 5 # liberal CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal[CMPS_2020_primary_sample_weighted$Q43 == 3] <- 4 # moderate CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal[CMPS_2020_primary_sample_weighted$Q43 == 4] <- 3 # somewhat conservative CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal[CMPS_2020_primary_sample_weighted$Q43 == 5] <- 2 # very conservative CMPS_2020_primary_sample_weighted$Ideology.Scale.Liberal[CMPS_2020_primary_sample_weighted$Q43 == 6] <- 1 # none of these ### Reject Ideology CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject[CMPS_2020_primary_sample_weighted$Q43 == 1] <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject[CMPS_2020_primary_sample_weighted$Q43 == 2] <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject[CMPS_2020_primary_sample_weighted$Q43 == 3] <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject[CMPS_2020_primary_sample_weighted$Q43 == 4] <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject[CMPS_2020_primary_sample_weighted$Q43 == 5] <- 0 CMPS_2020_primary_sample_weighted$Ideology.Scale.Reject[CMPS_2020_primary_sample_weighted$Q43 == 6] <- 1 # none of these # Gender (female) CMPS_2020_primary_sample_weighted$Gender <- 0 CMPS_2020_primary_sample_weighted$Gender[CMPS_2020_primary_sample_weighted$S3b == 1] <- 0 # Male CMPS_2020_primary_sample_weighted$Gender[CMPS_2020_primary_sample_weighted$S3b == 2] <- 1 # Female CMPS_2020_primary_sample_weighted$Gender[CMPS_2020_primary_sample_weighted$S3b == 3] <- NA # Non-binary CMPS_2020_primary_sample_weighted$Gender[CMPS_2020_primary_sample_weighted$S3b == 4] <- NA # Party Identification CMPS_2020_primary_sample_weighted$Party.ID <- NA CMPS_2020_primary_sample_weighted$Party.ID[CMPS_2020_primary_sample_weighted$Q21 == 1] <- "Republican" CMPS_2020_primary_sample_weighted$Party.ID[CMPS_2020_primary_sample_weighted$Q21 == 2] <- "Democrat" CMPS_2020_primary_sample_weighted$Party.ID[CMPS_2020_primary_sample_weighted$Q21 == 3] <- "Independent" CMPS_2020_primary_sample_weighted$Party.ID[CMPS_2020_primary_sample_weighted$Q21 == 4] <- "Other" # Party Identification (Democrat) CMPS_2020_primary_sample_weighted$Party.ID.Dem <- NA CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 1] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 2] <- 1 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 3] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 4] <- 0 # Party Identification (Strong Democrat) CMPS_2020_primary_sample_weighted$Party.ID.Dem <- NA CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 1] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 2] <- 1 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 2] <- 1 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 3] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Dem[CMPS_2020_primary_sample_weighted$Q21 == 4] <- 0 # Party Identification (Republican) CMPS_2020_primary_sample_weighted$Party.ID.Rep <- NA CMPS_2020_primary_sample_weighted$Party.ID.Rep[CMPS_2020_primary_sample_weighted$Q21 == 1] <- 1 CMPS_2020_primary_sample_weighted$Party.ID.Rep[CMPS_2020_primary_sample_weighted$Q21 == 2] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Rep[CMPS_2020_primary_sample_weighted$Q21 == 3] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Rep[CMPS_2020_primary_sample_weighted$Q21 == 4] <- 0 table(CMPS_2020_primary_sample_weighted$Party.ID.Rep) # Party Identification (Independent) CMPS_2020_primary_sample_weighted$Party.ID.Ind <- NA CMPS_2020_primary_sample_weighted$Party.ID.Ind[CMPS_2020_primary_sample_weighted$Q21 == 1] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Ind[CMPS_2020_primary_sample_weighted$Q21 == 2] <- 0 CMPS_2020_primary_sample_weighted$Party.ID.Ind[CMPS_2020_primary_sample_weighted$Q21 == 3] <- 1 CMPS_2020_primary_sample_weighted$Party.ID.Ind[CMPS_2020_primary_sample_weighted$Q21 == 4] <- 0 table(CMPS_2020_primary_sample_weighted$Party.ID.Rep) table(CMPS_2020_primary_sample_weighted$Party.ID.Dem) table(CMPS_2020_primary_sample_weighted$Party.ID.Ind) ### Point Scale (Democrat) CMPS_2020_primary_sample_weighted$Party.Scale.Dem <- NA CMPS_2020_primary_sample_weighted$Party.Scale.Dem[CMPS_2020_primary_sample_weighted$Q21 == 1 & CMPS_2020_primary_sample_weighted$Q22 == 2] <- 0 # not strong rep CMPS_2020_primary_sample_weighted$Party.Scale.Dem[CMPS_2020_primary_sample_weighted$Q21 == 1 & CMPS_2020_primary_sample_weighted$Q22 == 1] <- 0 # strong rep CMPS_2020_primary_sample_weighted$Party.Scale.Dem[CMPS_2020_primary_sample_weighted$Q21 == 2 & CMPS_2020_primary_sample_weighted$Q22 == 2] <- 1 # not strong dem CMPS_2020_primary_sample_weighted$Party.Scale.Dem[CMPS_2020_primary_sample_weighted$Q21 == 2 & CMPS_2020_primary_sample_weighted$Q22 == 1] <- 2 # strong dem table(CMPS_2020_primary_sample_weighted$Party.Scale.Dem) ### Creating a 7-Point Party Scale Democrats CMPS_2020_primary_sample_weighted <- CMPS_2020_primary_sample_weighted %>% mutate(Democratic.Partisanship.7P = case_when( CMPS_2020_primary_sample_weighted$Q21 == 1 & CMPS_2020_primary_sample_weighted$Q22 == 1 ~ 1, # Strong Republican CMPS_2020_primary_sample_weighted$Q21 == 2 & CMPS_2020_primary_sample_weighted$Q22 == 1 ~ 7, # Strong Dem CMPS_2020_primary_sample_weighted$Q21 == 1 ~ 2, # Republican CMPS_2020_primary_sample_weighted$Q23 == 1 ~ 3, # Lean Republican CMPS_2020_primary_sample_weighted$Q21 == 3 ~ 4, # Independent CMPS_2020_primary_sample_weighted$Q23 == 3 ~ 4, # Independent CMPS_2020_primary_sample_weighted$Q23 == 2 ~ 5, # Lean Dem CMPS_2020_primary_sample_weighted$Q21 == 2 ~ 6, # Democrat CMPS_2020_primary_sample_weighted$Q23 == 88 ~ NA, # Dont know TRUE ~ NA_integer_ )) ### Test 5 Point Scale CMPS_2020_primary_sample_weighted <- CMPS_2020_primary_sample_weighted %>% mutate(Five.Point.Scale.Dem = case_when( CMPS_2020_primary_sample_weighted$Q21 == 1 & CMPS_2020_primary_sample_weighted$Q22 == 1 ~ 1, # Strong rep CMPS_2020_primary_sample_weighted$Q21 == 2 & CMPS_2020_primary_sample_weighted$Q22 == 1 ~ 5, # strong dem CMPS_2020_primary_sample_weighted$Q21 == 1 ~ 2, # Republican CMPS_2020_primary_sample_weighted$Q21 == 3 ~ 3, # Independents CMPS_2020_primary_sample_weighted$Q21 == 4 ~ 3, # Independents CMPS_2020_primary_sample_weighted$Q21 == 2 ~ 4, # Democrats TRUE ~ NA_integer_ )) ### Strong Dem Binary CMPS_2020_primary_sample_weighted$Strong.Dem.Binary <- 0 CMPS_2020_primary_sample_weighted$Strong.Dem.Binary[CMPS_2020_primary_sample_weighted$Q21 == 2 & CMPS_2020_primary_sample_weighted$Q22 == 1] <- 1 table(CMPS_2020_primary_sample_weighted$Strong.Dem.Binary) ### Creating a 7-Point Party Scale Republicans CMPS_2020_primary_sample_weighted <- CMPS_2020_primary_sample_weighted %>% mutate(Republican.Partisanship = case_when( CMPS_2020_primary_sample_weighted$Q21 == 1 & CMPS_2020_primary_sample_weighted$Q22 == 1 ~ 7, # Strong CMPS_2020_primary_sample_weighted$Q21 == 2 & CMPS_2020_primary_sample_weighted$Q22 == 1 ~ 1, # Moved this condition up CMPS_2020_primary_sample_weighted$Q21 == 1 ~ 2, CMPS_2020_primary_sample_weighted$Q23 == 1 ~ 5, CMPS_2020_primary_sample_weighted$Q23 == 3 ~ 4, CMPS_2020_primary_sample_weighted$Q21 == 3 ~ 4, CMPS_2020_primary_sample_weighted$Q23 == 2 ~ 3, CMPS_2020_primary_sample_weighted$Q21 == 2 ~ 6, TRUE ~ NA_integer_ )) ### Language of Survey CMPS_2020_primary_sample_weighted$Survey.Language <- 0 CMPS_2020_primary_sample_weighted$Survey.Language[CMPS_2020_primary_sample_weighted$S1 == 1] <- 1 # English CMPS_2020_primary_sample_weighted$Survey.Language[CMPS_2020_primary_sample_weighted$S1 == 2] <- 2 # Spanish CMPS_2020_primary_sample_weighted$Survey.Language[CMPS_2020_primary_sample_weighted$S1 == 3] <- 0 CMPS_2020_primary_sample_weighted$Survey.Language[CMPS_2020_primary_sample_weighted$S1 == 4] <- 0 CMPS_2020_primary_sample_weighted$Survey.Language[CMPS_2020_primary_sample_weighted$S1 == 5] <- 0 CMPS_2020_primary_sample_weighted$Survey.Language[CMPS_2020_primary_sample_weighted$S1 == 6] <- 0 ### Language of Survey Spnaish CMPS_2020_primary_sample_weighted$Survey.Language.Spanish <- 0 CMPS_2020_primary_sample_weighted$Survey.Language.Spanish[CMPS_2020_primary_sample_weighted$S1 == 1] <- 0 # English CMPS_2020_primary_sample_weighted$Survey.Language.Spanish[CMPS_2020_primary_sample_weighted$S1 == 2] <- 1 # Spanish CMPS_2020_primary_sample_weighted$Survey.Language.Spanish[CMPS_2020_primary_sample_weighted$S1 == 3] <- 0 CMPS_2020_primary_sample_weighted$Survey.Language.Spanish[CMPS_2020_primary_sample_weighted$S1 == 4] <- 0 CMPS_2020_primary_sample_weighted$Survey.Language.Spanish[CMPS_2020_primary_sample_weighted$S1 == 5] <- 0 CMPS_2020_primary_sample_weighted$Survey.Language.Spanish[CMPS_2020_primary_sample_weighted$S1 == 6] <- 0 ### Income CMPS_2020_primary_sample_weighted$Income <- NA CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 1] <- 1 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 2] <- 2 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 3] <- 3 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 4] <- 4 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 5] <- 5 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 6] <- 6 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 7] <- 7 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 8] <- 8 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 9] <- 9 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 10] <- 10 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 11] <- 11 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 == 12] <- 12 CMPS_2020_primary_sample_weighted$Income[CMPS_2020_primary_sample_weighted$Q813 >= 90] <- NA #### Age CMPS_2020_primary_sample_weighted$Age <- NA CMPS_2020_primary_sample_weighted$Age[CMPS_2020_primary_sample_weighted$S5_Age == 2] <- 1 CMPS_2020_primary_sample_weighted$Age[CMPS_2020_primary_sample_weighted$S5_Age == 3] <- 2 CMPS_2020_primary_sample_weighted$Age[CMPS_2020_primary_sample_weighted$S5_Age == 4] <- 3 CMPS_2020_primary_sample_weighted$Age[CMPS_2020_primary_sample_weighted$S5_Age == 5] <- 4 CMPS_2020_primary_sample_weighted$Age[CMPS_2020_primary_sample_weighted$S5_Age == 6] <- 5 CMPS_2020_primary_sample_weighted$Age[CMPS_2020_primary_sample_weighted$S5_Age == 7] <- 6 table(CMPS_2020_primary_sample_weighted$S5_Age) CMPS.Latino.Adult$Age <- NA CMPS.Latino.Adult$Age[CMPS.Latino.Adult$S5_Age == 2] <- 1 # 18-29 CMPS.Latino.Adult$Age[CMPS.Latino.Adult$S5_Age == 3] <- 2 # 30-39 CMPS.Latino.Adult$Age[CMPS.Latino.Adult$S5_Age == 4] <- 3 # 40-49 CMPS.Latino.Adult$Age[CMPS.Latino.Adult$S5_Age == 5] <- 4 # 50-59 CMPS.Latino.Adult$Age[CMPS.Latino.Adult$S5_Age == 6] <- 5 # 60-69 CMPS.Latino.Adult$Age[CMPS.Latino.Adult$S5_Age == 7] <- 6 # 70+ ``` ## Seperating the Data by Race ```{r} # Primary Race Latino CMPS_2020_primary_sample_weighted$Latinx <- 0 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 2] <- 1 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 1] <- 0 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 3] <- 0 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 4] <- 0 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 5] <- 0 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 6] <- 0 CMPS_2020_primary_sample_weighted$Latinx[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 7] <- 0 # Latino, including white CMPS_2020_primary_sample_weighted$Latino_White <- 0 CMPS_2020_primary_sample_weighted$Latino_White[CMPS_2020_primary_sample_weighted$S2_Racer2 == 1] <-1 CMPS_2020_primary_sample_weighted$Latino_White[CMPS_2020_primary_sample_weighted$S2_Racer2 == 0] <-0 # Primary Race African American CMPS_2020_primary_sample_weighted$AfricanAmerican <- 0 CMPS_2020_primary_sample_weighted$AfricanAmerican[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 3] <- 1 summary(CMPS_2020_primary_sample_weighted$AfricanAmerican) # Primary Race Asian CMPS_2020_primary_sample_weighted$Asian <- 0 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 4] <- 1 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 2] <- 0 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 3] <- 0 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 1] <- 0 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 5] <- 0 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 6] <- 0 CMPS_2020_primary_sample_weighted$Asian[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 7] <- 0 summary(CMPS_2020_primary_sample_weighted$Asian) # Primary Race White CMPS_2020_primary_sample_weighted$White <- 0 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 1] <- 1 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 2] <- 0 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 3] <- 0 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 4] <- 0 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 5] <- 0 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 6] <- 0 CMPS_2020_primary_sample_weighted$White[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 7] <- 0 summary(CMPS_2020_primary_sample_weighted$White) ## Subset Data Frames by race for Adultagers CMPS.Latino.Adult <- CMPS_2020_primary_sample_weighted[CMPS_2020_primary_sample_weighted$Latinx == "1",] CMPS.Latino.Adult.Citizens <- CMPS.Latino.Adult[CMPS.Latino.Adult$Citizenship == "1",] CMPS.Latino.Adult.Protected.Status <- CMPS.Latino.Adult[CMPS.Latino.Adult$Protected.Status == "1",] CMPS.Latino.Adult.Non.Citizen <- CMPS.Latino.Adult[CMPS.Latino.Adult$Non.Citizen == "1",] CMPS.Black.Adult <- CMPS_2020_primary_sample_weighted[CMPS_2020_primary_sample_weighted$AfricanAmerican == "1",] CMPS.White.Adult <- CMPS_2020_primary_sample_weighted[CMPS_2020_primary_sample_weighted$White == "1",] CMPS.White.Latino.Adult <- CMPS_2020_primary_sample_weighted[CMPS_2020_primary_sample_weighted$Latino_White == "1",] CMPS.Asian.Adult <- CMPS_2020_primary_sample_weighted[CMPS_2020_primary_sample_weighted$S2_Race_Prime == 4,] ``` #################################################################################################### #################################################################################################### ################################################### Models and Analysis ########################### #################################################################################################### #################################################################################################### ################ Models with All Statuses Final ################ ```{r} # Latino Adults Am_ID_Latino_DACA <- lm(American.Identity ~ daca_personal + Education + Survey.Language.Spanish + Income + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender, data = CMPS.Latino.Adult) stargazer(Am_ID_Latino_DACA, type = "text") Am_ID_Latino_Citizens <- lm(American.Identity ~ Citizenship + Education + Survey.Language.Spanish + Income + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender, data = CMPS.Latino.Adult) stargazer(Am_ID_Latino_Citizens, type = "text") Am_ID_Latino_LPR <- lm(American.Identity ~ LPR + Education + Survey.Language.Spanish + Income + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender, data = CMPS.Latino.Adult) stargazer(Am_ID_Latino_LPR, type = "text") Am_ID_Latino_Visa <- lm(American.Identity ~ visa_holder + Education + Survey.Language.Spanish + Income + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender, data = CMPS.Latino.Adult) stargazer(Am_ID_Latino_LPR, type = "text") ##### Model with Citizenship as the Reference Am_ID_Latino_All_Id <- lm(American.Identity ~ daca_personal + LPR + visa_holder + Education + Survey.Language.Spanish + Income + Large.Urban.Community + Party.ID.Dem + Gender + Skin.Color, data = CMPS.Latino.Adult) stargazer(Am_ID_Latino_All_Id, type = "text") Am_ID_Latino_Youth_All_Id <- lm(American.Identity ~ daca_personal + LPR + visa_holder + Survey.Language.Spanish + Large.Urban.Community + Party.ID.Dem + Gender + SkinColor, data = CMPS.Latino.Teen) stargazer(Am_ID_Latino_Youth_All_Id, type = "text") ##### Viz stargazer(Am_ID_Latino_Youth_All_Id, Am_ID_Latino_All_Id, type = "text", column.labels = c("Latino Youth", "Latino Adults"), covariate.labels = c("DACA Recipient", "Legal Permanent Resident", "Visa Holder", "Parental Education", "Respondent Education", "Spanish Language", "Household Income", "Large Urban", "Small Suburban", "Rural", "Democrat", "Female", "Constant"), star.cutoffs = c(0.05, 0.01, 0.001), digits = 2) stargazer(Am_ID_Latino_Youth_All_Id, Am_ID_Latino_All_Id, type = "latex", title = "American Identity Valuation Among Latino Youth and Adults", dep.var.labels = "American Identity Valuation", column.labels = c("Youth (18-22)", "Adults (23+)"), covariate.labels = c("DACA Recipient", "Legal Permanent Resident", "Visa Holder", "Parental Education", "Respondent Education", "Spanish Language", "Household Income", "Large Urban Community", "Small Suburban Community", "Rural Community", "Democrat", "Female", "Constant"), notes = c("Reference category for immigration status: U.S. Citizens.", "Standard errors in parentheses.", "Youth model (ages 18-22) controls for parental education.", "Adult model (ages 23+) controls for respondent education.", "All models use survey weights for nationally representative estimates."), notes.align = "l", notes.append = FALSE, star.cutoffs = c(0.05, 0.01, 0.001), star.char = c("*", "**", "***"), omit.stat = c("f", "ser"), digits = 2, font.size = "small", no.space = TRUE, header = FALSE, table.placement = "H", out = "tables/table1_american_identity.tex") # Saves to file ``` ### Checking for missing data in models ```{r} ## Income ### Finding Missing # Check missing data on each variable in your model model_vars <- c("American.Identity", "daca_personal", "LPR", "visa_holder", "Education", "Survey.Language.Spanish", "Income", "Large.Urban.Community", "Small.Suburban.Community", "Rural.Community", "Party.ID.Dem", "Gender") cat("=== MISSING DATA ANALYSIS ===\n") cat("Total observations:", nrow(CMPS.Latino.Adult), "\n\n") # Check each variable for (var in model_vars) { n_missing <- sum(is.na(CMPS.Latino.Adult[[var]])) pct_missing <- 100 * n_missing / nrow(CMPS.Latino.Adult) cat(sprintf("%-30s Missing: %4d (%.1f%%)\n", var, n_missing, pct_missing)) } # Check complete cases complete_cases <- complete.cases(CMPS.Latino.Adult[, model_vars]) cat("\nComplete cases (no missing on any variable):", sum(complete_cases), "\n") cat("Cases with at least one missing value:", sum(!complete_cases), "\n") ``` ###### Multiple Imputation for Youth Parent's Education ```{r} ### Multiple Imputations for Parents Education install.packages("mice") install.packages("miceadds") library(mice) library(miceadds) imputation_vars <- c( # Variables to impute "Mother_Edu", "Father_Edu", # variables in model "American.Identity", "daca_personal", "LPR", "visa_holder", "Survey.Language.Spanish", "Large.Urban.Community", "Small.Suburban.Community", "Rural.Community", "Party.ID.Dem", "Gender", # Additional predictors "Parent_Foreign_Born" ) # variable check available_vars <- imputation_vars[imputation_vars %in% names(CMPS.Latino.Teen)] print(available_vars) # imputation dataset data_for_imputation <- CMPS.Latino.Teen[, available_vars] # missing data pattern cat("Missing data summary:\n") print(sapply(data_for_imputation, function(x) sum(is.na(x)))) cat("\nPercentage missing:\n") print(round(100 * sapply(data_for_imputation, function(x) sum(is.na(x)) / length(x)), 1)) # viz md.pattern(data_for_imputation) # multiple imputation set.seed(12345) # For reproducibility imputed_data <- mice( data_for_imputation, m = 10, method = "pmm", maxit = 20, seed = 12345, print = FALSE ) # convergence check plot(imputed_data) densityplot(imputed_data, ~Mother_Edu + Father_Edu) # Parent_Education / each imputed dataset create_parent_ed <- function(data) { data$Parent_Education <- pmax(data$Mother_Edu, data$Father_Edu, na.rm = TRUE) return(data) } # all imputed datasets as a list imputed_list <- complete(imputed_data, "all") # application imputed_list <- lapply(imputed_list, create_parent_ed) # conversion imputed_data_long <- complete(imputed_data, "long", include = TRUE) imputed_data_long$Parent_Education <- pmax(imputed_data_long$Mother_Edu, imputed_data_long$Father_Edu, na.rm = TRUE) imputed_final <- as.mids(imputed_data_long) # regression model on each imputed dataset fit_mi <- with(imputed_final, lm(American.Identity ~ daca_personal + LPR + visa_holder + Parent_Education + Survey.Language.Spanish + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender)) # pool results pooled_results <- pool(fit_mi) summary(pooled_results) # summary pooled_summary <- summary(pooled_results) print(pooled_summary, digits = 3) # origional model w listwise deletion complete_case_model <- lm(American.Identity ~ daca_personal + LPR + visa_holder + Parent_Education + Survey.Language.Spanish + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender, data = CMPS.Latino.Teen) # sample sizes cat("\n=== SAMPLE SIZE COMPARISON ===\n") cat("Complete case N:", length(complete_case_model$fitted.values), "\n") cat("MI N:", nrow(data_for_imputation), "\n") cat("Observations recovered:", nrow(data_for_imputation) - length(complete_case_model$fitted.values), "\n") # key coefficient (DACA) cat("\n=== DACA COEFFICIENT COMPARISON ===\n") cat("Complete case:", round(coef(complete_case_model)["daca_personal"], 3), " (SE:", round(summary(complete_case_model)$coefficients["daca_personal", "Std. Error"], 3), ")\n") cat("MI:", round(pooled_summary$estimate[pooled_summary$term == "daca_personal"], 3), " (SE:", round(pooled_summary$std.error[pooled_summary$term == "daca_personal"], 3), ")\n") fit_mi <- with(imputed_final, lm(American.Identity ~ daca_personal + LPR + visa_holder + Parent_Education + Survey.Language.Spanish + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender)) pooled_results <- pool(fit_mi) pooled_summary <- summary(pooled_results) print(pooled_summary) ``` ##### Single Imputation With Vizualization ```{r} # single-imputed dataset all_imputed <- complete(imputed_data, "all") Mother_Edu_avg <- rowMeans(sapply(all_imputed, function(df) df$Mother_Edu)) Father_Edu_avg <- rowMeans(sapply(all_imputed, function(df) df$Father_Edu)) CMPS.Latino.Teen$Parent_Education <- ifelse( is.na(CMPS.Latino.Teen$Mother_Edu) & is.na(CMPS.Latino.Teen$Father_Edu), round(pmax(Mother_Edu_avg, Father_Edu_avg)), pmax(CMPS.Latino.Teen$Mother_Edu, CMPS.Latino.Teen$Father_Edu, na.rm = TRUE) ) # Main Model Am_ID_Latino_Youth_All_Id <- lm(American.Identity ~ daca_personal + LPR + visa_holder + Parent_Education + Survey.Language.Spanish + Large.Urban.Community + Small.Suburban.Community + Rural.Community + Party.ID.Dem + Gender, data = CMPS.Latino.Teen) # table stargazer(Am_ID_Latino_Youth_All_Id, Am_ID_Latino_All_Id, type = "html", title = "American Identity Valuation Among Latino Youth and Adults", dep.var.labels = "American Identity Valuation", column.labels = c("Youth (18-22)", "Adults (23+)"), covariate.labels = c("DACA Recipient", "Legal Permanent Resident", "Visa Holder", "Parental Education", "Respondent Education", "Spanish Language", "Household Income", "Large Urban Community", "Small Suburban Community", "Rural Community", "Democrat", "Female", "Constant"), # Notes notes = c("Reference category for immigration status: U.S. Citizens.", "* p<0.05; ** p<0.01; *** p<0.001"), notes.align = "l", # Formatting star.cutoffs = c(0.05, 0.01, 0.001), digits = 3, no.space = TRUE, omit.stat = c("f", "ser"), # Output file out = "tables/table1_american_identity.html") cat("✓ HTML table saved to: tables/table1_american_identity.html\n") cat(" Open this file in a browser and copy-paste into Word\n") ``` ### Create a flex table (Table 1. Descriptive Statistics) ```{r} install.packages("flextable") library(flextable) install.packages("officer") library(officer) # Get coefficients youth_results <- summary(Am_ID_Latino_Youth_All_Id)$coefficients adult_results <- summary(Am_ID_Latino_All_Id)$coefficients # Helper function format_coef <- function(coef_matrix, var_name) { if (var_name %in% rownames(coef_matrix)) { est <- coef_matrix[var_name, "Estimate"] se <- coef_matrix[var_name, "Std. Error"] p <- coef_matrix[var_name, "Pr(>|t|)"] stars <- ifelse(p < 0.001, "***", ifelse(p < 0.01, "**", ifelse(p < 0.05, "*", ""))) return(list( coef = sprintf("%.3f%s", est, stars), se = sprintf("(%.3f)", se) )) } else { return(list(coef = "—", se = "")) } } # Define variables all_vars <- c("(Intercept)", "daca_personal", "LPR", "visa_holder", "Parent_Education", "Education", "Survey.Language.Spanish", "Income", "Large.Urban.Community", "Small.Suburban.Community", "Rural.Community", "Party.ID.Dem", "Gender") var_labels <- c("Constant", "DACA Recipient", "Legal Permanent Resident", "Visa Holder", "Parental Education", "Respondent Education", "Spanish Language", "Household Income", "Large Urban Community", "Small Suburban Community", "Rural Community", "Democrat", "Female") # Extract coefficients youth_data <- lapply(all_vars, function(v) format_coef(youth_results, v)) adult_data <- lapply(all_vars, function(v) format_coef(adult_results, v)) # stacking data rows_list <- list() for (i in seq_along(var_labels)) { # Coefficient row rows_list[[length(rows_list) + 1]] <- data.frame( Variable = var_labels[i], Youth = youth_data[[i]]$coef, Adult = adult_data[[i]]$coef, stringsAsFactors = FALSE ) # SE row (blank variable name) rows_list[[length(rows_list) + 1]] <- data.frame( Variable = "", Youth = youth_data[[i]]$se, Adult = adult_data[[i]]$se, stringsAsFactors = FALSE ) } # Combine all rows table_data <- do.call(rbind, rows_list) # Remove rows where both models have "—" table_data <- table_data[!(table_data$Youth == "—" & table_data$Adult == "—"), ] # Create flextable ft <- flextable(table_data) ft <- set_header_labels(ft, Variable = "", Youth = "Youth (18-22)", Adult = "Adults (23+)" ) # Format ft <- theme_booktabs(ft) ft <- fontsize(ft, size = 11, part = "all") ft <- font(ft, fontname = "Times New Roman", part = "all") ft <- align(ft, align = "center", part = "header") ft <- align(ft, j = 2:3, align = "center", part = "body") ft <- align(ft, j = 1, align = "left", part = "body") ft <- width(ft, j = 1, width = 2.5) ft <- width(ft, j = 2:3, width = 1.5) # Add borders (publication style) ft <- border_remove(ft) ft <- hline_top(ft, border = fp_border(width = 2), part = "header") ft <- hline_bottom(ft, border = fp_border(width = 2), part = "body") ft <- hline(ft, border = fp_border(width = 1), part = "header") # Add footer n_youth <- nobs(Am_ID_Latino_Youth_All_Id) n_adult <- nobs(Am_ID_Latino_All_Id) r2_youth <- summary(Am_ID_Latino_Youth_All_Id)$r.squared r2_adult <- summary(Am_ID_Latino_All_Id)$r.squared ft <- add_footer_lines(ft, values = c( sprintf("N = %d (Youth), %d (Adults)", n_youth, n_adult), sprintf("R² = %.3f (Youth), %.3f (Adults)", r2_youth, r2_adult), "Note: Reference: U.S. Citizens. Standard errors in parentheses. * p<0.05, ** p<0.01, *** p<0.001" )) ft <- fontsize(ft, size = 9, part = "footer") ft <- align(ft, align = "left", part = "footer") # Save doc <- read_docx() doc <- body_add_par(doc, "Table 1. American Identity Valuation Among Latino Youth and Adults", style = "heading 1") doc <- body_add_flextable(doc, ft) print(doc, target = "tables/table1_american_identity.docx") cat("✓ Word table saved to: tables/table1_american_identity.docx\n") ``` ##### General Statistics ```{r} library(flextable) library(officer) # Youth statistics youth_stats <- data.frame( Group = "Latino Youth", N = sum(!is.na(CMPS.Latino.Teen$American.Identity)), Mean = mean(CMPS.Latino.Teen$American.Identity, na.rm = TRUE), SD = sd(CMPS.Latino.Teen$American.Identity, na.rm = TRUE), Median = median(CMPS.Latino.Teen$American.Identity, na.rm = TRUE), # Categories (higher = stronger) High = 100 * mean(CMPS.Latino.Teen$American.Identity >= 6 & CMPS.Latino.Teen$American.Identity <= 8, na.rm = TRUE), Medium = 100 * mean(CMPS.Latino.Teen$American.Identity >= 3 & CMPS.Latino.Teen$American.Identity <= 5, na.rm = TRUE), Low = 100 * mean(CMPS.Latino.Teen$American.Identity >= 1 & CMPS.Latino.Teen$American.Identity <= 2, na.rm = TRUE) ) # Adult statistics adult_stats <- data.frame( Group = "Latino Adults", N = sum(!is.na(CMPS.Latino.Adult$American.Identity)), Mean = mean(CMPS.Latino.Adult$American.Identity, na.rm = TRUE), SD = sd(CMPS.Latino.Adult$American.Identity, na.rm = TRUE), Median = median(CMPS.Latino.Adult$American.Identity, na.rm = TRUE), High = 100 * mean(CMPS.Latino.Adult$American.Identity >= 6 & CMPS.Latino.Adult$American.Identity <= 8, na.rm = TRUE), Medium = 100 * mean(CMPS.Latino.Adult$American.Identity >= 3 & CMPS.Latino.Adult$American.Identity <= 5, na.rm = TRUE), Low = 100 * mean(CMPS.Latino.Adult$American.Identity >= 1 & CMPS.Latino.Adult$American.Identity <= 2, na.rm = TRUE) ) # Combine table_data <- rbind(youth_stats, adult_stats) # fomrat numebrs final_table <- data.frame( Group = table_data$Group, N = table_data$N, Mean = sprintf("%.2f", table_data$Mean), SD = sprintf("(%.2f)", table_data$SD), Median = sprintf("%.2f", table_data$Median), High = sprintf("%.1f%%", table_data$High), Medium = sprintf("%.1f%%", table_data$Medium), Low = sprintf("%.1f%%", table_data$Low) ) # CREATE FLEXTABLE ft <- flextable(final_table) # Set column headers ft <- set_header_labels(ft, Group = "Group", N = "N", Mean = "Mean", SD = "SD", Median = "Median", High = "High (6-8)", Medium = "Medium (3-5)", Low = "Low (1-2)" ) # Add grouped header row ft <- add_header_row(ft, values = c("", "Central Tendency", "Distribution (%)"), colwidths = c(2, 3, 3) ) # format ft <- theme_booktabs(ft) ft <- fontsize(ft, size = 11, part = "all") ft <- font(ft, fontname = "Times New Roman", part = "all") ft <- align(ft, align = "center", part = "header") ft <- align(ft, j = 1, align = "left", part = "body") ft <- align(ft, j = 2:8, align = "center", part = "body") # Column widths ft <- width(ft, j = 1, width = 1.5) ft <- width(ft, j = 2, width = 0.6) ft <- width(ft, j = 3:5, width = 0.8) ft <- width(ft, j = 6:8, width = 1.0) # broders ft <- border_remove(ft) ft <- hline_top(ft, border = fp_border(width = 2), part = "header") ft <- hline_bottom(ft, border = fp_border(width = 2), part = "body") ft <- hline(ft, i = 1, border = fp_border(width = 1), part = "header") ft <- hline(ft, i = 2, border = fp_border(width = 1), part = "header") # note ft <- add_footer_lines(ft, values = "Note: American Identity measured on 1-8 scale, with 8 indicating strongest identification.") ft <- fontsize(ft, size = 9, part = "footer") ft <- align(ft, align = "left", part = "footer") ft <- italic(ft, part = "footer") # save / file doc <- read_docx() doc <- body_add_par(doc, "Table X. Descriptive Statistics: American Identity Valuation Among Latino Youth and Adults", style = "heading 1") doc <- body_add_flextable(doc, ft) print(doc, target = "tables/descriptive_stats.docx") cat("✓ Descriptive statistics table saved to: tables/descriptive_stats.docx\n") cat("\nActual values:\n") print(final_table) ``` ######## Visualizing American Identity Acorss Age Cohorts ```{r} #### Packages library(dplyr) library(haven) install.packages("ggplot2") library(ggplot2) #### clearing old Data CMPS.Latino.Adult <- CMPS.Latino.Adult %>% select(-any_of("daca_personal")) CMPS.Latino.Teen <- CMPS.Latino.Teen %>% select(-any_of("daca_personal")) # adult dataset CMPS.Latino.Adult <- zap_labels(CMPS.Latino.Adult) # youth dataset CMPS.Latino.Teen <- zap_labels(CMPS.Latino.Teen) # Adult CMPS.Latino.Adult <- CMPS.Latino.Adult %>% mutate(daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, Q470 == 2 ~ 0, Q470 == 1 & Q471r1 != 1 ~ 0, TRUE ~ NA_real_ )) # Youth CMPS.Latino.Teen <- CMPS.Latino.Teen %>% mutate(daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, Q470 == 2 ~ 0, Q470 == 1 & Q471r1 != 1 ~ 0, TRUE ~ NA_real_ )) # combine CMPS.Latino.Combined <- bind_rows(CMPS.Latino.Adult, CMPS.Latino.Teen) cat("Combined dataset N:", nrow(CMPS.Latino.Combined), "\n") cat("DACA recipients:", sum(CMPS.Latino.Combined$daca_personal == 1, na.rm = TRUE), "\n") # create Age groups CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate(Age = case_when( S5_Age == 1 ~ 1, # 16-17 S5_Age == 2 ~ 2, # 18-29 S5_Age == 3 ~ 3, # 30-39 S5_Age == 4 ~ 4, # 40-49 S5_Age == 5 ~ 5, # 50-59 S5_Age == 6 ~ 6, # 60-69 S5_Age == 7 ~ 7, # 70+ TRUE ~ NA_real_ )) # DACA eligibility criteria. Recoded to NA. CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate(daca_personal = ifelse(daca_personal == 1 & Age >= 5, NA_real_, daca_personal)) CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate(Age = ifelse(daca_personal == 1 & Age == 4, 3, Age)) # American Identity (reverse code) CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate(American.Identity = case_when( Q560r8 == 1 ~ 8, Q560r8 == 2 ~ 7, Q560r8 == 3 ~ 6, Q560r8 == 4 ~ 5, Q560r8 == 5 ~ 4, Q560r8 == 6 ~ 3, Q560r8 == 7 ~ 2, Q560r8 == 8 ~ 1, TRUE ~ NA_real_ )) # calculate means by age cohort age_identity_daca_combined <- CMPS.Latino.Combined %>% filter(daca_personal == 1, !is.na(Age), !is.na(American.Identity)) %>% group_by(Age) %>% summarise( mean_identity = mean(American.Identity, na.rm = TRUE), se = sd(American.Identity, na.rm = TRUE) / sqrt(n()), n = n() ) %>% mutate(age_label = factor(Age, levels = 1:7, labels = c("16-17", "18-29", "30-39", "40-49", "50-59", "60-69", "70+"))) # sample sizes cat("\n=== DACA Recipients by Age Group ===\n") print(age_identity_daca_combined) # plot ggplot(age_identity_daca_combined, aes(x = age_label, y = mean_identity, group = 1)) + geom_line(color = "#2C7BB6", size = 1.2) + geom_point(color = "#2C7BB6", size = 3) + geom_errorbar(aes(ymin = mean_identity - 1.96 * se, ymax = mean_identity + 1.96 * se), width = 0.2, color = "#2C7BB6", linewidth = 1) + labs(title = "American Identity Among Latino DACA Recipients Across the Life Cycle", x = "Age Group", y = "Mean American Identity (1-8)") + scale_y_continuous(limits = c(1, 8), breaks = 1:8) + theme_minimal() + theme( plot.title = element_text(size = 14, face = "bold"), axis.title = element_text(size = 12), axis.text = element_text(size = 11) ) ##### Plot with Two Groups # Calculate means for DACA / Non recipients age_daca <- CMPS.Latino.Combined %>% filter(daca_personal == 1) %>% group_by(Age) %>% summarise(mean_identity = mean(American.Identity, na.rm = TRUE), se = sd(American.Identity, na.rm = TRUE) / sqrt(n())) %>% filter(!is.na(Age)) %>% mutate(group = "DACA Recipients") age_nondaca <- CMPS.Latino.Combined %>% filter(daca_personal == 0) %>% group_by(Age) %>% summarise(mean_identity = mean(American.Identity, na.rm = TRUE), se = sd(American.Identity, na.rm = TRUE) / sqrt(n())) %>% filter(!is.na(Age)) %>% mutate(group = "Non-DACA Latinos") age_combined <- bind_rows(age_daca, age_nondaca) %>% mutate(age_label = factor(Age, levels = 1:7, labels = c("16-17", "18-29", "30-39", "40-49", "50-59", "60-69", "70+"))) # Plot with two lines ggplot(age_combined, aes(x = age_label, y = mean_identity, group = group, color = group)) + geom_line(size = 1) + geom_point(size = 3) + geom_errorbar(aes(ymin = mean_identity - 1.96 * se, ymax = mean_identity + 1.96 * se), width = 0.2) + scale_color_manual(values = c("DACA Recipients" = "black", "Non-DACA Latinos" = "gray")) + labs(title = "American Identity Valuations Among Latinos Across the Life Cycle", x = "Age", y = "Mean American Identity (1-8)", color = "") + theme_minimal() ``` ############################## Second Attempt at Age Group DATA Visualization ################################# ```{r} library(dplyr) library(ggplot2) library(haven) # Ensure clean datasets CMPS.Latino.Adult <- zap_labels(CMPS.Latino.Adult) CMPS.Latino.Teen <- zap_labels(CMPS.Latino.Teen) # Add sample identifiers CMPS.Latino.Adult <- CMPS.Latino.Adult %>% mutate(sample = "adult") CMPS.Latino.Teen <- CMPS.Latino.Teen %>% mutate(sample = "youth") # Combine CMPS.Latino.Combined <- bind_rows(CMPS.Latino.Adult, CMPS.Latino.Teen) # Rebuild key variables on combined dataset CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate( # American Identity reverse coded 1-8 American.Identity = case_when( Q560r8 == 1 ~ 8, Q560r8 == 2 ~ 7, Q560r8 == 3 ~ 6, Q560r8 == 4 ~ 5, Q560r8 == 5 ~ 4, Q560r8 == 6 ~ 3, Q560r8 == 7 ~ 2, Q560r8 == 8 ~ 1, TRUE ~ NA_real_ ), # DACA personal daca_personal = case_when( Q470 == 1 & Q471r1 == 1 ~ 1, Q470 == 2 ~ 0, Q470 == 1 & Q471r1 != 1 ~ 0, TRUE ~ NA_real_ ), # Age groups matching 2020 figure Age.Group = case_when( S5_Age == 1 ~ "16-17", S5_Age == 2 ~ "18-29", S5_Age == 3 ~ "30-39", S5_Age == 4 ~ "40-49", S5_Age == 5 ~ "50-59", S5_Age == 6 ~ "60-69", S5_Age == 7 ~ "70+", TRUE ~ NA_character_ ), Age.Group.Num = case_when( S5_Age == 1 ~ 1, S5_Age == 2 ~ 2, S5_Age == 3 ~ 3, S5_Age == 4 ~ 4, S5_Age == 5 ~ 5, S5_Age == 6 ~ 6, S5_Age == 7 ~ 7, TRUE ~ NA_real_ ), Age.Group = factor(Age.Group, levels = c("16-17", "18-29", "30-39", "40-49", "50-59", "60-69", "70+")) ) # Remove implausible DACA cases (born before 1981) CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate( daca_personal = ifelse(daca_personal == 1 & Age.Group.Num >= 5, NA_real_, daca_personal) ) # Build Status.Plot (DACA vs Citizen only) CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate( Status.Plot = case_when( daca_personal == 1 ~ "DACA Recipients", Citizenship == 1 ~ "Latino Citizens", TRUE ~ NA_character_ )) # Check cell sizes CMPS.Latino.Combined %>% filter(!is.na(Status.Plot), !is.na(Age.Group)) %>% count(Age.Group, Status.Plot) # Residualize American Identity controlling for covariates # Youth model model_youth_2020 <- lm(American.Identity ~ Survey.Language.Spanish + Parent_Education + Large.Urban.Community + Party.ID.Dem + Gender, data = filter(CMPS.Latino.Combined, sample == "youth", Status.Plot %in% c("DACA Recipients", "Latino Citizens"), !is.na(American.Identity))) # Adult model model_adult_2020 <- lm(American.Identity ~ Survey.Language.Spanish + Education + Income + Large.Urban.Community + Party.ID.Dem + Gender, data = filter(CMPS.Latino.Combined, sample == "adult", Status.Plot %in% c("DACA Recipients", "Latino Citizens"), !is.na(American.Identity), !is.na(Age.Group))) # Grand mean for recentering grand_mean_2020 <- mean(CMPS.Latino.Combined$American.Identity, na.rm = TRUE) # Add residuals to dataset CMPS.Latino.Combined <- CMPS.Latino.Combined %>% mutate(American.Identity.Adj = NA_real_) youth_idx <- which(CMPS.Latino.Combined$sample == "youth" & CMPS.Latino.Combined$Status.Plot %in% c("DACA Recipients", "Latino Citizens") & !is.na(CMPS.Latino.Combined$American.Identity)) CMPS.Latino.Combined$American.Identity.Adj[youth_idx] <- residuals(model_youth_2020) + grand_mean_2020 adult_idx <- which(CMPS.Latino.Combined$sample == "adult" & CMPS.Latino.Combined$Status.Plot %in% c("DACA Recipients", "Latino Citizens") & !is.na(CMPS.Latino.Combined$American.Identity) & !is.na(CMPS.Latino.Combined$Age.Group)) CMPS.Latino.Combined$American.Identity.Adj[adult_idx] <- residuals(model_adult_2020) + grand_mean_2020 # Rebuild adult index to match model's complete cases exactly adult_data <- CMPS.Latino.Combined %>% mutate(row_id = row_number()) %>% filter( sample == "adult", Status.Plot %in% c("DACA Recipients", "Latino Citizens"), !is.na(American.Identity), !is.na(Age.Group), !is.na(Survey.Language.Spanish), !is.na(Education), !is.na(Income), !is.na(Large.Urban.Community), !is.na(Party.ID.Dem), !is.na(Gender) ) # Rerun adult model on this clean subset model_adult_2020 <- lm(American.Identity ~ Survey.Language.Spanish + Education + Income + Large.Urban.Community + Party.ID.Dem + Gender, data = adult_data) # Assign residuals using row_id to ensure correct alignment CMPS.Latino.Combined$American.Identity.Adj[adult_data$row_id] <- residuals(model_adult_2020) + grand_mean_2020 # Do the same for youth youth_data <- CMPS.Latino.Combined %>% mutate(row_id = row_number()) %>% filter( sample == "youth", Status.Plot %in% c("DACA Recipients", "Latino Citizens"), !is.na(American.Identity), !is.na(Survey.Language.Spanish), !is.na(Parent_Education), !is.na(Large.Urban.Community), !is.na(Party.ID.Dem), !is.na(Gender) ) model_youth_2020 <- lm(American.Identity ~ Survey.Language.Spanish + Parent_Education + Large.Urban.Community + Party.ID.Dem + Gender, data = youth_data) CMPS.Latino.Combined$American.Identity.Adj[youth_data$row_id] <- residuals(model_youth_2020) + grand_mean_2020 # Compute adjusted means identity_means_2020 <- CMPS.Latino.Combined %>% filter(!is.na(Status.Plot), !is.na(Age.Group), !is.na(American.Identity.Adj)) %>% mutate(Age.Group = as.character(Age.Group)) %>% group_by(Age.Group, Status.Plot) %>% summarise( mean_identity = mean(American.Identity.Adj, na.rm = TRUE), se = sd(American.Identity.Adj, na.rm = TRUE) / sqrt(n()), n = n(), .groups = "drop" ) %>% mutate( # Force minimum se for tiny cells se = case_when(n < 5 ~ pmax(se, 0.5), TRUE ~ se), Age.Group = factor(Age.Group, levels = c("16-17", "18-29", "30-39", "40-49", "50-59", "60-69", "70+")) ) print(identity_means_2020) # Plot ggplot(identity_means_2020, aes(x = Age.Group, y = mean_identity, group = Status.Plot, color = Status.Plot, shape = Status.Plot)) + geom_line(linewidth = 0.8, na.rm = TRUE) + geom_point(size = 3, na.rm = TRUE) + geom_errorbar( aes(ymin = mean_identity - 1.96 * se, ymax = pmin(mean_identity + 1.96 * se, 8)), width = 0.2, na.rm = TRUE ) + scale_color_manual( values = c( "DACA Recipients" = "black", "Latino Citizens" = "grey60" )) + scale_shape_manual( values = c( "DACA Recipients" = 16, "Latino Citizens" = 16 )) + scale_y_continuous( limits = c(1, 8), breaks = seq(1, 8, 1) ) + labs( title = "American Identity Valuation Across the Life Cycle", subtitle = "CMPS 2020 Latino Respondents — Covariate Adjusted", x = "Age Group", y = "Adjusted Mean American Identity Valuation (1-8)", color = NULL, shape = NULL, caption = "Note: Means adjusted for language, education, income, community size,\npartisanship, and gender. Error bars represent 95% confidence intervals.\nDACA recipient estimates based on small sample sizes in youth and older age groups." ) + theme_minimal(base_size = 13) + theme( plot.title = element_text(face = "bold"), legend.position = "bottom", panel.grid.major.x = element_blank(), plot.caption = element_text(hjust = 0), plot.caption.position = "plot" ) # Bar Chart identity_means_2020 %>% filter(Age.Group %in% c("16-17", "18-29", "30-39", "40-49")) %>% ggplot(aes(x = Age.Group, y = mean_identity, fill = Status.Plot)) + geom_col( position = position_dodge(width = 0.7), width = 0.6, na.rm = TRUE ) + geom_errorbar( aes(ymin = mean_identity - 1.96 * se, ymax = pmin(mean_identity + 1.96 * se, 8)), position = position_dodge(width = 0.7), width = 0.25, na.rm = TRUE ) + scale_fill_manual( values = c( "DACA Recipients" = "black", "Latino Citizens" = "grey60" ) ) + scale_y_continuous( limits = c(0, 8), breaks = seq(0, 8, 1), expand = expansion(mult = c(0, 0.02)) ) + labs( title = "American Identity Valuation By Age Cohort", subtitle = "CMPS 2020 Latino Respondents — Covariate Adjusted", x = "Age Group", y = "Adjusted Mean American Identity Valuation", fill = NULL, caption = "Note: Means adjusted for language, education, income, community size,\npartisanship, and gender. Error bars represent 95% confidence intervals.\nDACA recipient estimates based on small sample sizes in youth and older age groups." ) + theme_minimal(base_size = 13) + theme( plot.title = element_text(face = "bold"), legend.position = "bottom", panel.grid.major.x = element_blank(), plot.caption = element_text(hjust = 0), plot.caption.position = "plot" ) ``` ##### Clustered Bar Plot with Two Groups (Figure 1 Final) ```{r} # Descriptive means (raw, no adjustment) identity_means_descriptive <- CMPS.Latino.Combined %>% filter( Status.Plot %in% c("DACA Recipients", "Latino Citizens"), Age.Group %in% c("16-17", "18-29", "30-39", "40-49"), !is.na(American.Identity) ) %>% group_by(Age.Group, Status.Plot) %>% summarise( mean_identity = mean(American.Identity, na.rm = TRUE), se = sd(American.Identity, na.rm = TRUE) / sqrt(n()), n = n(), .groups = "drop" ) %>% mutate( Age.Group = factor(Age.Group, levels = c("16-17", "18-29", "30-39", "40-49")) ) # Descriptive, no error bars p_descriptive <- ggplot(identity_means_descriptive, aes(x = Age.Group, y = mean_identity, fill = Status.Plot)) + geom_col( position = position_dodge(width = 0.7), width = 0.6 ) + scale_fill_manual( values = c( "DACA Recipients" = "black", "Latino Citizens" = "grey60" ) ) + scale_y_continuous( limits = c(0, 8), breaks = seq(0, 8, 1), expand = expansion(mult = c(0, 0.02)) ) + facet_wrap(~ Status.Plot, ncol = 2) + labs( title = "American Identity Valuation by Age Cohort", subtitle = "Descriptive Means", x = "Age Group", y = "Mean American Identity Valuation (1-8)", fill = NULL, caption = "Note: Bars represent unadjusted group means. Covariate-adjusted estimates show the same pattern \n(see Appendix B)." ) + theme_minimal(base_size = 13) + theme( plot.title = element_text(face = "bold"), legend.position = "none", strip.text = element_text(face = "bold", size = 12), panel.grid.major.x = element_blank(), plot.caption = element_text(hjust = 0), plot.caption.position = "plot" ) # Covariate-adjusted, with error bars (Appendix A) p_adjusted <- identity_means_2020 %>% filter(Age.Group %in% c("16-17", "18-29", "30-39", "40-49")) %>% ggplot(aes(x = Age.Group, y = mean_identity, fill = Status.Plot)) + geom_col( position = position_dodge(width = 0.7), width = 0.6 ) + geom_errorbar( aes(ymin = mean_identity - 1.96 * se, ymax = pmin(mean_identity + 1.96 * se, 8)), position = position_dodge(width = 0.7), width = 0.25 ) + scale_fill_manual( values = c( "DACA Recipients" = "black", "Latino Citizens" = "grey60" ) ) + scale_y_continuous( limits = c(0, 8), breaks = seq(0, 8, 1), expand = expansion(mult = c(0, 0.02)) ) + facet_wrap(~ Status.Plot, ncol = 2) + labs( x = "Age Group", y = "Adjusted Mean American Identity Valuation", fill = NULL, caption = "Note: Means adjusted for language, education, income, community size,\npartisanship, and gender. Error bars represent 95% confidence intervals.\nDACA recipient estimates based on small sample sizes." ) + theme_minimal(base_size = 13) + theme( plot.title = element_text(face = "bold"), legend.position = "none", strip.text = element_text(face = "bold", size = 12), panel.grid.major.x = element_blank(), plot.caption = element_text(hjust = 0), plot.caption.position = "plot" ) # Print both p_descriptive p_adjusted # Cell means and gap table identity_means_descriptive %>% select(Age.Group, Status.Plot, mean_identity, n) %>% pivot_wider( names_from = Status.Plot, values_from = c(mean_identity, n) ) %>% mutate( gap = `mean_identity_Latino Citizens` - `mean_identity_DACA Recipients`, pct_gap = gap / `mean_identity_Latino Citizens` * 100 ) %>% arrange(Age.Group) ``` ```{r} identity_means_2020 %>% select(Age.Group, Status.Plot, mean_identity) %>% pivot_wider(names_from = Status.Plot, values_from = mean_identity) %>% mutate(gap = `Latino Citizens` - `DACA Recipients`) ```