2

Loading Data

question1:

salary <- read.csv("Professorial salaries.csv")
head(salary)

##   ID      Rank Discipline Yrs.since.phd Yrs.service  Sex NPubs Ncits Salary
## 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

##question2:

library(GGally)

## Loading required package: ggplot2

## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2

vars = salary[, 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`.

question3

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 + Salary | Sex, data = salary)

	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]
Salary
Mean (SD)	101000 (26000)	115000 (30400)	114000 (30300)
Median [Min, Max]	104000 [62900, 161000]	108000 [57800, 232000]	107000 [57800, 232000]