#install.packages("readr")
library(readr)
library(knitr)
voterdata<-read_csv("/Users/meiminshan/Desktop/Abbreviated Dataset Labeled(October Only)(1).csv")
## Parsed with column specification:
## cols(
##   .default = col_character(),
##   NumChildren = col_double()
## )
## See spec(...) for full column specifications.
head(voterdata)
## # A tibble: 6 x 34
##   gender race  education familyincome children region urbancity Vote2012
##   <chr>  <chr> <chr>     <chr>        <chr>    <chr>  <chr>     <chr>   
## 1 Female White 4-year    Prefer not … No       West   Suburb    Barack …
## 2 Female White Some Col… $60K-$69,999 No       West   Rural Ar… Mitt Ro…
## 3 Male   White High Sch… $50K-$59,999 No       Midwe… City      Mitt Ro…
## 4 Male   White Some Col… $70K-$79,999 No       South  City      Barack …
## 5 Male   White 4-year    $40K-$49,999 No       South  Suburb    Mitt Ro…
## 6 Female White 2-year    $30K-$39,999 No       West   Suburb    Barack …
## # … with 26 more variables: Vote2016 <chr>, TrumpSanders <chr>,
## #   PartyRegistration <chr>, PartyIdentification <chr>,
## #   PartyIdentification2 <chr>, PartyIdentification3 <chr>,
## #   NewsPublicAffairs <chr>, DemPrimary <chr>, RepPrimary <chr>,
## #   ImmigrantContributions <chr>, ImmigrantNaturalization <chr>,
## #   ImmigrationShouldBe <chr>, Abortion <chr>, GayMarriage <chr>,
## #   DeathPenalty <chr>, DeathPenaltyFreq <chr>, TaxWealthy <chr>,
## #   Healthcare <chr>, GlobWarmExist <chr>, GlobWarmingSerious <chr>,
## #   AffirmativeAction <chr>, Religion <chr>, ReligiousImportance <chr>,
## #   ChurchAttendance <chr>, PrayerFrequency <chr>, NumChildren <dbl>

Crosstabs

Do male & female respondents differ in whether or not they think it should be easier or harder for foreigners to immigrate to the United States legally?

Yes, it appears that men think it should be easier for foreigners to immigrate to the United States legally more than women. Women think it should be harder for foreigners to immigrate to the United States legally more than men.

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
voterdata%>%
  group_by(gender, ImmigrationShouldBe)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))
## # A tibble: 14 x 4
## # Groups:   gender [2]
##    gender ImmigrationShouldBe     n percent
##    <chr>  <chr>               <int>   <dbl>
##  1 Female Much Easier           306 0.0754 
##  2 Female Much Harder          1078 0.266  
##  3 Female No change             856 0.211  
##  4 Female Not Sure              385 0.0948 
##  5 Female Slightly Easier       641 0.158  
##  6 Female Slightly Harder       767 0.189  
##  7 Female <NA>                   27 0.00665
##  8 Male   Much Easier           414 0.105  
##  9 Male   Much Harder           788 0.2    
## 10 Male   No change            1062 0.270  
## 11 Male   Not Sure              169 0.0429 
## 12 Male   Slightly Easier       792 0.201  
## 13 Male   Slightly Harder       689 0.175  
## 14 Male   <NA>                   26 0.00660
library(ggplot2)
voterdata%>%
  group_by(gender, ImmigrationShouldBe)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))%>%
  ggplot()+
  geom_col(aes(x=gender, y=percent, fill=ImmigrationShouldBe))

According to the bar graph, it reveals that men are more likely to believe it should be easier for foreigners to immigrate to the United States legally than women. Women are more likely to believe it should be harder for foreigners to immigrate to the United States legally than men.

Do male & female respondents differ in their support for allowing gays and lesbians to marry legally?

Yes, it appears that women are supporting gays and lesbians to marry legally more than men. Men are more likely to disagree gays and lesbians to marry legally than women.

library(dplyr)
voterdata%>%
  group_by(gender, GayMarriage)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))
## # A tibble: 8 x 4
## # Groups:   gender [2]
##   gender GayMarriage     n percent
##   <chr>  <chr>       <int>   <dbl>
## 1 Female Favor        2014 0.496  
## 2 Female Not sure      548 0.135  
## 3 Female Oppose       1487 0.366  
## 4 Female <NA>           11 0.00271
## 5 Male   Favor        1579 0.401  
## 6 Male   Not sure      406 0.103  
## 7 Male   Oppose       1937 0.492  
## 8 Male   <NA>           18 0.00457
library(ggplot2)
voterdata%>%
  group_by(GayMarriage,gender)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))%>%
ggplot()+
  geom_col(aes(x=gender, y=percent, fill=GayMarriage))

According to the bar graph, women mostly show support for gays and lesbians to marry legally. Men mostly oppose gays and lesbians to marry legally.

Do different ethnic groups differ in having number of children?

Yes, it appears that Black, Hispanic, Mixed, Native American Mixed, Other and White are more likely to have 0 children. Asian and Middle Eastern are more likely to have no more than 3 children.

library(dplyr)
voterdata%>%
  group_by(race, NumChildren)%>%
  summarize(n=n())%>%
  mutate((percent=n/sum(n)))
## # A tibble: 63 x 4
## # Groups:   race [9]
##    race  NumChildren     n `(percent = n/sum(n))`
##    <chr>       <dbl> <int>                  <dbl>
##  1 Asian           0    75                0.625  
##  2 Asian           1    23                0.192  
##  3 Asian           2    16                0.133  
##  4 Asian           3     3                0.025  
##  5 Asian          NA     3                0.025  
##  6 Black           0   506                0.752  
##  7 Black           1    79                0.117  
##  8 Black           2    50                0.0743 
##  9 Black           3    22                0.0327 
## 10 Black           4     4                0.00594
## # … with 53 more rows
library(ggplot2)
voterdata%>%
  group_by(race, NumChildren)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))%>%
  ggplot()+
  geom_col(aes(x=race, y=percent, fill=NumChildren))

According to the bar graph, it reveals that Asian mostly has 1 or 2 children or 0 children.

Black mostly has 0 children and could have more 3 children.

Hispanic mostly has 0 children and could have more 3 children.

Middle Eastern mostly has 2 or 3 children, but no more than 3 children.

Mixed mostly has 0 children and could have more 3 children.

Native American Mixed mostly has 1 children or 0 children and could have more than 3 children.

Other mostly has 0 children and could have more than 3 children.

White mostly has 0 children and could have more than 3 children.

Do male and female responders differ in their support for raising taxes on families with incomes over $200,000 per year?

Yes, it appears that female responders are more likely to support raising taxes on families with incomes over $200, 000 per year. Male responders are more likely to oppose raising taxes on families with incomes over $200, 000 per year.

library(dplyr)
voterdata%>%
  group_by(gender, TaxWealthy)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))
## # A tibble: 8 x 4
## # Groups:   gender [2]
##   gender TaxWealthy     n percent
##   <chr>  <chr>      <int>   <dbl>
## 1 Female Favor       2706 0.667  
## 2 Female Not sure     513 0.126  
## 3 Female Oppose       827 0.204  
## 4 Female <NA>          14 0.00345
## 5 Male   Favor       2068 0.525  
## 6 Male   Not sure     293 0.0744 
## 7 Male   Oppose      1568 0.398  
## 8 Male   <NA>          11 0.00279
library(ggplot2)
voterdata%>%
  group_by(TaxWealthy, gender)%>%
  summarize(n=n())%>%
  mutate(percent=n/sum(n))%>%
  ggplot()+
  geom_col(aes(x=gender, y=percent, fill=TaxWealthy))

According to the bar graph, women mostly show support for raising taxes on families with incomes over $200, 000 per year. Men mostly oppose raising taxes on families with incomes over $200, 000 per year.

Conclusions