Title: “Homework 1”

Author: “Bryan Solomon”

Date: “01 September, 2021”

The Histogram of the Sam Houston University staff displays the salaries of 2,225 Sam Houston University staff members. The histogram is unimodal with a single peak and is positively skewed with a majority of occurrences to the left of the graph It has a minimum salary of $6,012 and a max salary of 456,216 for the Dean of Osteopathic Medicine. The average salary of Sam Houston University employee is $63,821.58 and the median is $55,485. The mean is influenced by the outliers, which consist of salaries greater than $300,00.00. A problem with the presentation of the histogram is that it does not show specific salaries for positions, but instead plots them according to salary amount in dollars.

library(readr, quietly = TRUE)
salaries = read_csv(file = "C:\\Users\\USER\\Desktop\\Sam Houston Salaries.csv")
names(salaries) = tolower(names(salaries))
hist(salaries$annual_salary)

Greatest histogram

library(ggplot2)
library(scales)

## 
## Attaching package: 'scales'

## The following object is masked from 'package:readr':
## 
##     col_factor

ggplot(data = salaries,mapping = aes(annual_salary))+geom_histogram(binwidth=9379.2)+ggtitle(label="Distribution of Salaries")+xlab(label="Annual Salaries")+scale_x_continuous(labels=label_dollar())

Final histogram

summary(cars$dist)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    2.00   26.00   36.00   42.98   56.00  120.00

summary(cars$speed)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##     4.0    12.0    15.0    15.4    19.0    25.0

library(ggplot2)
library(scales)
ggplot(data = salaries,mapping = aes(annual_salary))+geom_histogram(binwidth=9379.2)+ggtitle(label="Distribution of Salaries")+xlab(label="Annual Salaries")+scale_x_continuous(labels=label_dollar())

change bins

library(ggplot2)
library(scales)
ggplot(data = salaries,mapping = aes(annual_salary))+geom_histogram(binwidth=9379.25)+ggtitle(label="Distribution of Salaries")+xlab(label="Annual Salaries")+scale_x_continuous(labels=label_dollar())

summary(salaries)

##  position_title     home_organization_desc annual_salary   
##  Length:2225        Length:2225            Min.   :  6012  
##  Class :character   Class :character       1st Qu.: 40950  
##  Mode  :character   Mode  :character       Median : 55485  
##                                            Mean   : 63822  
##                                            3rd Qu.: 76770  
##                                            Max.   :456216

# data points: 2,225
# bins: take square root and round up: 48
geom_histogram(binwidth=9379.25)

## geom_bar: na.rm = FALSE, orientation = NA
## stat_bin: binwidth = 9379.25, bins = NULL, na.rm = FALSE, orientation = NA, pad = FALSE
## position_stack

ggplot(data = salaries,mapping = aes(annual_salary, stat=..density..))+geom_density()+ggtitle(label="Distribution of Salaries")+xlab(label="Annual Salaries")+scale_x_continuous(labels=label_dollar())

summary(salaries)

##  position_title     home_organization_desc annual_salary   
##  Length:2225        Length:2225            Min.   :  6012  
##  Class :character   Class :character       1st Qu.: 40950  
##  Mode  :character   Mode  :character       Median : 55485  
##                                            Mean   : 63822  
##                                            3rd Qu.: 76770  
##                                            Max.   :456216