Task 2

library(ggplot2)
library(readxl)
Business_School <- read_excel("R Take Home Exam 2024/Task 2/Business School.xlsx")

head(Business_School)

## # A tibble: 6 × 9
##   `Student ID` `Undergrad Degree` `Undergrad Grade` `MBA Grade`
##          <dbl> <chr>                          <dbl>       <dbl>
## 1            1 Business                        68.4        90.2
## 2            2 Computer Science                70.2        68.7
## 3            3 Finance                         76.4        83.3
## 4            4 Business                        82.6        88.7
## 5            5 Finance                         76.9        75.4
## 6            6 Computer Science                83.3        82.1
## # ℹ 5 more variables: `Work Experience` <chr>, `Employability (Before)` <dbl>,
## #   `Employability (After)` <dbl>, Status <chr>, `Annual Salary` <dbl>

ggplot(Business_School, aes(x = `Undergrad Degree`)) +
  geom_bar() +
  labs(title = "Distribution of Undergraduate Degrees",
       x = "Undergrad Degree",
       y = "Count")

summary(Business_School$`Annual Salary`)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   20000   87125  103500  109058  124000  340000

ggplot(Business_School, aes(x = `Annual Salary`)) +
  geom_histogram(binwidth = 10000) +
  labs(title = "Distribution of Annual Salary",
       x = "Annual Salary",
       y = "Number of Students")

t.test(Business_School$`MBA Grade`, mu = 74)

## 
##  One Sample t-test
## 
## data:  Business_School$`MBA Grade`
## t = 2.6587, df = 99, p-value = 0.00915
## alternative hypothesis: true mean is not equal to 74
## 95 percent confidence interval:
##  74.51764 77.56346
## sample estimates:
## mean of x 
##  76.04055