-
Notifications
You must be signed in to change notification settings - Fork 0
/
individual1.Rmd
86 lines (67 loc) · 2.5 KB
/
individual1.Rmd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
---
title: "Lab 3"
author: "Felix Baez-Santiago"
date: "3/1/2021"
output: html_document
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
Imports
```{r}
library(dplyr)
library(ggplot2)
df <- readxl::read_xls("./GSS.xls")
head(df)
names(df)
df <- df %>%
rename(gss = `Gss year for this respondent`, happy = `General happiness`, party = `Political party affiliation`, sex = `Respondents sex`, educ = `Highest year of school completed`, divorce = `Ever been divorced or separated`, marital_status = `Marital status`, employ = `Labor force status`, id = `Respondent id number`, ballot = `Ballot used for interview`, )
df$highestSchool = as.numeric(as.character(df$educ))
```
#Question 1.
#Find the average years of education for the respondents with each marital status. Arrange your output in a meaningful order and print. Describe any patterns you find.
```{r}
df %>%
mutate(avg_educ = as.numeric(educ)) %>%
na.omit %>%
group_by(marital_status) %>%
summarize(mean(avg_educ)
)
head(df)
```
#Question 2.
#Create a single data frame containing records for the better educated respondents with each marital status. A “better educated” respondent is someone who has strictly more years of education than the average among those with the same marital status. Print the structure of the data frame.
```{r}
ques2 <- df %>%
mutate(avg_school_completed = as.numeric(educ)) %>%
na.omit %>%
group_by(marital_status) %>%
summarize(betterEduc = (educ > avg_school_completed))
str(ques2)
names(df)
```
#Question 3.
#How is the happiness of a respondent related to his/her marriage status? Define that a person is happy if the response to question is “Very happy” or “Pretty happy”.
```{r}
```
#Question 4.
#Does party affiliation affect the relationship you found in the last question?
```{r}
```
#Question 5.
#How is marital status related to the education of a respondent? What are possible reasons accounting for the patterns you see?
```{r}
ggplot(df, aes(x = party, y = highestSchool)) + geom_boxplot() + theme(axis.text.x = element_text(angle = 90))
```
#Question 6.
#Explore two more interesting questions, and answer those questions using the GSS data.
```{r}
ggplot(df, aes(x=sex, fill=happy))+geom_bar(position='fill')
```
Males and females reported very similar levels of happiness.
```{r}
ggplot(df, aes(x=sex, y=highestSchool))+geom_boxplot()
names(df)
```
Females and Males have similar mean for their highest level of education, but males have a higher third quartile than females.
```