##install.packages("utf8")
##install.packages("ggstatsplot")

library(here)
library(readr)
library(ggstatsplot)
library(purrr)
library(tidyverse)
library(ggpubr)
library(rstatix)
library(qqplotr)
library(jtools) 
library(DT)
options(scipen=999)

Introduction

For this assignment I decided to learn something about extramarial affairs. I wanted to know which gender was more likely to have an extramatrial affair. I found a data set called “Fair’s Extramarital Affairs Data”. This data was collected in 1969 and contains 601 observations of 9 variables about how many extramartial affairs people had over a 12 month period. The variables in the dataset include age, gender, education, occupation, religiousness, and children. Personally, I approached this assignment with a bias towards men engaging in more extramartial affairs than women.

Sources

Click here to view all data sources || Click here to view Data Source Description

Data Gathering, Collation and Simple Bar Chart

In the code chunk below I am gathering the data from a remote data source (line 45). In lines 48 through 57 I am giving the columns in dataframe meaningful titles. I am converting the Number of Years column to Number of Months because its easier to work with integers. On line 63 I am removing the observation that did not contain at least 1 affair. The data is displayed in tabular format on line 65 and a simple bar chart is created on lines 67 and 68.

dat <- read_csv('https://raw.githubusercontent.com/greerda/Data607/main/Affairs.csv')
## Rows: 601 Columns: 10
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): gender, children
## dbl (8): rownames, affairs, age, yearsmarried, religiousness, education, occ...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
df_affairs <- dat|> select(`Number of Affairs` = affairs,
                            Age = age,
                            Gender =gender,
                           `Months Married`= yearsmarried,
                           `Has Children` = children,
                           `Religiosity Level (1-5)`= religiousness,
                            `Highest Grade Level Achieved` =education,
                           `Level of Satisfaction with Marriage (1-5)`= rating)

df_affairs$`Months Married`<- round(df_affairs$`Months Married`*12,0)

df_affairs<-df_affairs|>filter(`Number of Affairs`>0)

datatable(df_affairs)
ggplot(df_affairs, aes(x=Gender, y=`Number of Affairs`, fill=Gender) )+
          geom_bar(stat = "identity" )+theme_minimal()+ggtitle("Number of Extra Martial Affairs by Gender")

Conclusion and Recommendations

After performing this basic analysis I was surprised that my personal biases were overturned. I initially thought that men would have a exponentially greater number of extramartial affairs. Based on this information I recommend that men should buy their wives flowers periodically when they go to Costco.