Task 1 Read the “Professorial Salaries” and name this dataset “salary”

library(readr)
Professorial_Salaries <- read_csv("C:/Users/24928614/Downloads/Professorial Salaries.csv")
## Rows: 397 Columns: 9
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Rank, Discipline, Sex
## dbl (6): ID, Yrs.since.phd, Yrs.service, NPubs, Ncits, Salary
## 
## 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.
head(Professorial_Salaries)
## # A tibble: 6 × 9
##      ID Rank      Discipline Yrs.since.phd Yrs.service Sex   NPubs Ncits Salary
##   <dbl> <chr>     <chr>              <dbl>       <dbl> <chr> <dbl> <dbl>  <dbl>
## 1     1 Prof      B                     19          18 Male     18    50 139750
## 2     2 Prof      B                     20          16 Male      3    26 173200
## 3     3 AsstProf  B                      4           3 Male      2    50  79750
## 4     4 Prof      B                     45          39 Male     17    34 115000
## 5     5 Prof      B                     40          41 Male     11    41 141500
## 6     6 AssocProf B                      6           6 Male      6    37  97000

Task 2 Examine the overall relationship between variables

#install.packages("GGall"); 
library(GGally)
## Loading required package: ggplot2
## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2
vars = Professorial_Salaries[, c("Rank", "Discipline", "Yrs.since.phd",
"Yrs.service", "NPubs", "Ncits", "Sex", "Salary")]
ggpairs(data = vars, mapping = aes(color = Sex))
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

Task 3 Describe the study population

#install.packages("table1")
library(table1)
## 
## Attaching package: 'table1'
## The following objects are masked from 'package:base':
## 
##     units, units<-
table1(~ Rank + Discipline + Yrs.since.phd + Yrs.service + NPubs + Ncits | Sex, data = Professorial_Salaries)
Female
(N=39)		 Male
(N=358)		 Overall
(N=397)
Rank
AssocProf 10 (25.6%) 54 (15.1%) 64 (16.1%)
AsstProf 11 (28.2%) 56 (15.6%) 67 (16.9%)
Prof 18 (46.2%) 248 (69.3%) 266 (67.0%)
Discipline
A 18 (46.2%) 163 (45.5%) 181 (45.6%)
B 21 (53.8%) 195 (54.5%) 216 (54.4%)
Yrs.since.phd
Mean (SD) 16.5 (9.78) 22.9 (13.0) 22.3 (12.9)
Median [Min, Max] 17.0 [2.00, 39.0] 22.0 [1.00, 56.0] 21.0 [1.00, 56.0]
Yrs.service
Mean (SD) 11.6 (8.81) 18.3 (13.2) 17.6 (13.0)
Median [Min, Max] 10.0 [0, 36.0] 18.0 [0, 60.0] 16.0 [0, 60.0]
NPubs
Mean (SD) 20.2 (14.4) 17.9 (13.9) 18.2 (14.0)
Median [Min, Max] 18.0 [1.00, 50.0] 13.0 [1.00, 69.0] 13.0 [1.00, 69.0]
Ncits
Mean (SD) 40.7 (16.2) 40.2 (17.0) 40.2 (16.9)
Median [Min, Max] 36.0 [14.0, 70.0] 35.0 [1.00, 90.0] 35.0 [1.00, 90.0]

##Task 4 Describe the study population with mean (SD) presented for continuous variables

#install.packages("table1")
library(table1)
table1(~ Rank + Discipline + Yrs.since.phd + Yrs.service + NPubs + Ncits | Sex, data = Professorial_Salaries, render.continuous = c(. = "Median [Q1, Q3]"))
Female
(N=39)		 Male
(N=358)		 Overall
(N=397)
Rank
AssocProf 10 (25.6%) 54 (15.1%) 64 (16.1%)
AsstProf 11 (28.2%) 56 (15.6%) 67 (16.9%)
Prof 18 (46.2%) 248 (69.3%) 266 (67.0%)
Discipline
A 18 (46.2%) 163 (45.5%) 181 (45.6%)
B 21 (53.8%) 195 (54.5%) 216 (54.4%)
Yrs.since.phd
Median [Q1, Q3] 17.0 [10.0, 23.5] 22.0 [12.0, 33.0] 21.0 [12.0, 32.0]
Yrs.service
Median [Q1, Q3] 10.0 [4.00, 17.5] 18.0 [7.00, 27.0] 16.0 [7.00, 27.0]
NPubs
Median [Q1, Q3] 18.0 [11.0, 27.0] 13.0 [8.00, 25.8] 13.0 [8.00, 26.0]
Ncits
Median [Q1, Q3] 36.0 [28.5, 54.5] 35.0 [28.0, 50.0] 35.0 [28.0, 50.0]

Task 5 Compare characteristics of female professors and male professors

#install.packages("compareGroups")
library(compareGroups)
createTable(compareGroups(Sex ~ Rank + Discipline + Yrs.since.phd + Yrs.service + NPubs + Ncits, data = Professorial_Salaries))
## 
## --------Summary descriptives table by 'Sex'---------
## 
## _______________________________________________ 
##                 Female       Male     p.overall 
##                  N=39        N=358              
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ 
## Rank:                                   0.014   
##     AssocProf 10 (25.6%)  54 (15.1%)            
##     AsstProf  11 (28.2%)  56 (15.6%)            
##     Prof      18 (46.2%)  248 (69.3%)           
## Discipline:                             1.000   
##     A         18 (46.2%)  163 (45.5%)           
##     B         21 (53.8%)  195 (54.5%)           
## Yrs.since.phd 16.5 (9.78) 22.9 (13.0)  <0.001   
## Yrs.service   11.6 (8.81) 18.3 (13.2)  <0.001   
## NPubs         20.2 (14.4) 17.9 (13.9)   0.352   
## Ncits         40.7 (16.2) 40.2 (17.0)   0.851   
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯

#Task 6 Post the exercise into your Rpubs account