In the above example, the employ_2019 variable will break up my respondents into two groups (full-time and part-time employees), and the other four variables represents the behavior/attitudes which I will be investigating as I compare full-time employees and part-time employees.
library(readr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(ggplot2)
## Warning in file(con, "r"): cannot open file '/var/db/timezone/zoneinfo/
## +VERSION': No such file or directory
Voter2019 <- read_csv("/Users/chelsyrodriguez/Downloads/Voter Data 2019.csv")
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## .default = col_double(),
## weight_18_24_2018 = col_logical(),
## izip_2019 = col_character(),
## housevote_other_2019 = col_character(),
## senatevote_other_2019 = col_character(),
## senatevote2_other_2019 = col_character(),
## SenCand1Name_2019 = col_character(),
## SenCand1Party_2019 = col_character(),
## SenCand2Name_2019 = col_character(),
## SenCand2Party_2019 = col_character(),
## SenCand3Name_2019 = col_character(),
## SenCand3Party_2019 = col_character(),
## SenCand1Name2_2019 = col_character(),
## SenCand1Party2_2019 = col_character(),
## SenCand2Name2_2019 = col_character(),
## SenCand2Party2_2019 = col_character(),
## SenCand3Name2_2019 = col_character(),
## SenCand3Party2_2019 = col_character(),
## governorvote_other_2019 = col_character(),
## GovCand1Name_2019 = col_character(),
## GovCand1Party_2019 = col_character()
## # ... with 108 more columns
## )
## ℹ Use `spec()` for the full column specifications.
## Warning: 800 parsing failures.
## row col expected actual file
## 2033 weight_18_24_2018 1/0/T/F/TRUE/FALSE .917710168467982 '/Users/chelsyrodriguez/Downloads/Voter Data 2019.csv'
## 2828 weight_18_24_2018 1/0/T/F/TRUE/FALSE 1.41022291345592 '/Users/chelsyrodriguez/Downloads/Voter Data 2019.csv'
## 4511 weight_18_24_2018 1/0/T/F/TRUE/FALSE 1.77501243840922 '/Users/chelsyrodriguez/Downloads/Voter Data 2019.csv'
## 7264 weight_18_24_2018 1/0/T/F/TRUE/FALSE 1.29486870319614 '/Users/chelsyrodriguez/Downloads/Voter Data 2019.csv'
## 7277 weight_18_24_2018 1/0/T/F/TRUE/FALSE 1.44972719707603 '/Users/chelsyrodriguez/Downloads/Voter Data 2019.csv'
## .... ................. .................. ................ ......................................................
## See problems(...) for more details.
head(Voter2019)
## # A tibble: 6 x 1,282
## weight_2016 weight_2017 weight_panel_20… weight_latino_2… weight_18_24_20…
## <dbl> <dbl> <dbl> <dbl> <lgl>
## 1 0.358 0.438 0.503 NA NA
## 2 0.563 0.366 0.389 NA NA
## 3 0.552 0.550 0.684 NA NA
## 4 0.208 NA NA NA NA
## 5 0.334 0.346 0.322 NA NA
## 6 0.207 0.148 0.594 NA NA
## # … with 1,277 more variables: weight_overall_2018 <dbl>, weight_2019 <dbl>,
## # weight1_2018 <dbl>, weight1_2019 <dbl>, weight2_2019 <dbl>,
## # weight3_2019 <dbl>, cassfullcd <dbl>, vote2020_2019 <dbl>,
## # trumpapp_2019 <dbl>, fav_trump_2019 <dbl>, fav_obama_2019 <dbl>,
## # fav_hrc_2019 <dbl>, fav_sanders_2019 <dbl>, fav_putin_2019 <dbl>,
## # fav_schumer_2019 <dbl>, fav_pelosi_2019 <dbl>, fav_comey_2019 <dbl>,
## # fav_mueller_2019 <dbl>, fav_mcconnell_2019 <dbl>, fav_kavanaugh_2019 <dbl>,
## # fav_biden_2019 <dbl>, fav_warren_2019 <dbl>, fav_harris_2019 <dbl>,
## # fav_gillibrand_2019 <dbl>, fav_patrick_2019 <dbl>, fav_booker_2019 <dbl>,
## # fav_garcetti_2019 <dbl>, fav_klobuchar_2019 <dbl>, fav_gorsuch_2019 <dbl>,
## # fav_kasich_2019 <dbl>, fav_haley_2019 <dbl>, fav_bloomberg_2019 <dbl>,
## # fav_holder_2019 <dbl>, fav_avenatti_2019 <dbl>, fav_castro_2019 <dbl>,
## # fav_landrieu_2019 <dbl>, fav_orourke_2019 <dbl>,
## # fav_hickenlooper_2019 <dbl>, fav_pence_2019 <dbl>, add_confirm_2019 <dbl>,
## # izip_2019 <chr>, votereg_2019 <dbl>, votereg_f_2019 <dbl>,
## # regzip_2019 <dbl>, region_2019 <dbl>, turnout18post_2019 <dbl>,
## # tsmart_G2018_2019 <dbl>, tsmart_G2018_vote_type_2019 <dbl>,
## # tsmart_P2018_2019 <dbl>, tsmart_P2018_party_2019 <dbl>,
## # tsmart_P2018_vote_type_2019 <dbl>, housevote_2019 <dbl>,
## # housevote_other_2019 <chr>, senatevote_2019 <dbl>,
## # senatevote_other_2019 <chr>, senatevote2_2019 <dbl>,
## # senatevote2_other_2019 <chr>, SenCand1Name_2019 <chr>,
## # SenCand1Party_2019 <chr>, SenCand2Name_2019 <chr>,
## # SenCand2Party_2019 <chr>, SenCand3Name_2019 <chr>,
## # SenCand3Party_2019 <chr>, SenCand1Name2_2019 <chr>,
## # SenCand1Party2_2019 <chr>, SenCand2Name2_2019 <chr>,
## # SenCand2Party2_2019 <chr>, SenCand3Name2_2019 <chr>,
## # SenCand3Party2_2019 <chr>, governorvote_2019 <dbl>,
## # governorvote_other_2019 <chr>, GovCand1Name_2019 <chr>,
## # GovCand1Party_2019 <chr>, GovCand2Name_2019 <chr>,
## # GovCand2Party_2019 <chr>, GovCand3Name_2019 <chr>,
## # GovCand3Party_2019 <chr>, inst_court_2019 <dbl>, inst_media_2019 <dbl>,
## # inst_congress_2019 <dbl>, inst_justice_2019 <dbl>, inst_FBI_2019 <dbl>,
## # inst_military_2019 <dbl>, inst_church_2019 <dbl>, inst_business_2019 <dbl>,
## # Democrats_2019 <dbl>, Republicans_2019 <dbl>, Men_2019 <dbl>,
## # Women_2019 <dbl>, wm_2019 <dbl>, ww_2019 <dbl>, bm_2019 <dbl>,
## # bw_2019 <dbl>, hm_2019 <dbl>, hw_2019 <dbl>, rwm_2019 <dbl>,
## # rww_2019 <dbl>, rbm_2019 <dbl>, rbw_2019 <dbl>, pwm_2019 <dbl>, …
Voter2019 %>%
mutate(Employmentstatus = ifelse(employ_2019==1,"Full-time",
ifelse(employ_2019==2,"Part-time","NA")),
SatisfiedlifeJob = ifelse(satisf_Job_2018==1,"Very satisfied",
ifelse(satisf_Job_2018==2,"Somewhat satisfied",
ifelse(satisf_Job_2018==3,"Neither satisfied nor dissatisfied",
ifelse(satisf_Job_2018==4,"Somewhat dissatisfied","NA")))),
SatisfiedlifeIncome = ifelse(satisf_Income_2018==1,"Very satisfied",
ifelse(satisf_Income_2018==2,"Somewhat satisfied",
ifelse(satisf_Income_2018==3,"Neither satisfied nor dissatisfied",
ifelse(satisf_Income_2018==4,"Somewhat dissatisfied",
ifelse(satisf_Income_2018==5,"Very dissatisfied","NA"))))),
DifferenceIncome = ifelse(diff_inc_2019==1,"Strongly agree",
ifelse(diff_inc_2019==2,"Somewhat agree",
ifelse(diff_inc_2019==3,"Neither agree or disagree",
ifelse(diff_inc_2019==4,"Somewhat disagree",
ifelse(diff_inc_2019==5,"Strongly disagree",
ifelse(diff_inc_2019==8,"skipped","NA")))))),
FeelingAboutWelfareRecipients = ifelse(wr_2019>100,NA,wr_2019))%>%
select(Employmentstatus,SatisfiedlifeJob,SatisfiedlifeIncome,DifferenceIncome,FeelingAboutWelfareRecipients)%>%
filter(Employmentstatus %in% c("Full-time","Part-time"))
## # A tibble: 3,394 x 5
## Employmentstatus SatisfiedlifeJob SatisfiedlifeIn… DifferenceIncome
## <chr> <chr> <chr> <chr>
## 1 Full-time <NA> <NA> Strongly agree
## 2 Full-time Very satisfied Neither satisfi… Strongly disagr…
## 3 Full-time <NA> <NA> Somewhat agree
## 4 Part-time Neither satisfi… Very dissatisfi… Strongly agree
## 5 Full-time Very satisfied Very satisfied Somewhat agree
## 6 Part-time Neither satisfi… Somewhat dissat… Strongly agree
## 7 Full-time Somewhat satisf… Somewhat satisf… Strongly disagr…
## 8 Full-time <NA> <NA> Strongly disagr…
## 9 Full-time <NA> <NA> Strongly disagr…
## 10 Full-time <NA> <NA> Somewhat disagr…
## # … with 3,384 more rows, and 1 more variable:
## # FeelingAboutWelfareRecipients <dbl>