```{r}library(readxl)} library(tidyverse)

df <- read_excel(file.choose()) head(df)

Creating histogram of Wage to examine its distribution

ggplot(df, aes(x=Wage)) + geom_histogram(bins=30, fill=“skyblue”, color=“black”)

Creating boxplot to compare wage distribution between men and women

ggplot(df, aes(x=factor(Female), y=Wage)) + geom_boxplot(fill=c(“lightblue”,“pink”))

Calculating summary statistics of wage by gender

df %>% group_by(Female) %>% summarise(mean_wage = mean(Wage), median_wage = median(Wage), sd_wage = sd(Wage), min_wage = min(Wage), max_wage = max(Wage))

Calculating raw wage gap (mean wage difference between men and women)

mean(df\(Wage[df\)Female==0]) - mean(df\(Wage[df\)Female==1])

Creating log-transformed wage variable for better distribution properties

df\(l_wage <- log(df\)Wage)

Creating histogram of log(wage) to reduce skewness

ggplot(df, aes(x=l_wage)) + geom_histogram(bins=30, fill=“orange”)

Comparing log(wage) distribution between genders

ggplot(df, aes(x=factor(Female), y=l_wage)) + geom_boxplot()

Calculating approximate percentage wage gap using log differences

mean(df\(l_wage[df\)Female==0]) - mean(df\(l_wage[df\)Female==1])

Creating frequency table of education levels by gender

table(df\(Educ, df\)Female)

Calculating proportion of part-time workers by gender

df %>% group_by(Female) %>% summarise(parttime_rate = mean(Parttime))

Comparing average age between men and women

df %>% group_by(Female) %>% summarise(mean_age = mean(Age), median_age = median(Age))

Creating labels for better looking charts

df\(Gender <- factor(df\)Female, levels = c(0, 1), labels = c(“Men”, “Women”))

```