MBA Starting Salaries
Upanya Singh
26 December 2017
Mini Project - MBA Starting Salaries
Setting directory path and reading the file :
setwd("C:/Users/HP/Downloads/Intern/WEEK 4 DAY 1")
mbasalary.df <- read.csv(paste("MBA Starting Salaries Data.csv", sep=""))
View(mbasalary.df)
summary(mbasalary.df)## age sex gmat_tot gmat_qpc
## Min. :22.00 Min. :1.000 Min. :450.0 Min. :28.00
## 1st Qu.:25.00 1st Qu.:1.000 1st Qu.:580.0 1st Qu.:72.00
## Median :27.00 Median :1.000 Median :620.0 Median :83.00
## Mean :27.36 Mean :1.248 Mean :619.5 Mean :80.64
## 3rd Qu.:29.00 3rd Qu.:1.000 3rd Qu.:660.0 3rd Qu.:93.00
## Max. :48.00 Max. :2.000 Max. :790.0 Max. :99.00
## gmat_vpc gmat_tpc s_avg f_avg
## Min. :16.00 Min. : 0.0 Min. :2.000 Min. :0.000
## 1st Qu.:71.00 1st Qu.:78.0 1st Qu.:2.708 1st Qu.:2.750
## Median :81.00 Median :87.0 Median :3.000 Median :3.000
## Mean :78.32 Mean :84.2 Mean :3.025 Mean :3.062
## 3rd Qu.:91.00 3rd Qu.:94.0 3rd Qu.:3.300 3rd Qu.:3.250
## Max. :99.00 Max. :99.0 Max. :4.000 Max. :4.000
## quarter work_yrs frstlang salary
## Min. :1.000 Min. : 0.000 Min. :1.000 Min. : 0
## 1st Qu.:1.250 1st Qu.: 2.000 1st Qu.:1.000 1st Qu.: 0
## Median :2.000 Median : 3.000 Median :1.000 Median : 999
## Mean :2.478 Mean : 3.872 Mean :1.117 Mean : 39026
## 3rd Qu.:3.000 3rd Qu.: 4.000 3rd Qu.:1.000 3rd Qu.: 97000
## Max. :4.000 Max. :22.000 Max. :2.000 Max. :220000
## satis
## Min. : 1.0
## 1st Qu.: 5.0
## Median : 6.0
## Mean :172.2
## 3rd Qu.: 7.0
## Max. :998.0library(psych)
describe(mbasalary.df)## vars n mean sd median trimmed mad min max
## age 1 274 27.36 3.71 27 26.76 2.97 22 48
## sex 2 274 1.25 0.43 1 1.19 0.00 1 2
## gmat_tot 3 274 619.45 57.54 620 618.86 59.30 450 790
## gmat_qpc 4 274 80.64 14.87 83 82.31 14.83 28 99
## gmat_vpc 5 274 78.32 16.86 81 80.33 14.83 16 99
## gmat_tpc 6 274 84.20 14.02 87 86.12 11.86 0 99
## s_avg 7 274 3.03 0.38 3 3.03 0.44 2 4
## f_avg 8 274 3.06 0.53 3 3.09 0.37 0 4
## quarter 9 274 2.48 1.11 2 2.47 1.48 1 4
## work_yrs 10 274 3.87 3.23 3 3.29 1.48 0 22
## frstlang 11 274 1.12 0.32 1 1.02 0.00 1 2
## salary 12 274 39025.69 50951.56 999 33607.86 1481.12 0 220000
## satis 13 274 172.18 371.61 6 91.50 1.48 1 998
## range skew kurtosis se
## age 26 2.16 6.45 0.22
## sex 1 1.16 -0.66 0.03
## gmat_tot 340 -0.01 0.06 3.48
## gmat_qpc 71 -0.92 0.30 0.90
## gmat_vpc 83 -1.04 0.74 1.02
## gmat_tpc 99 -2.28 9.02 0.85
## s_avg 2 -0.06 -0.38 0.02
## f_avg 4 -2.08 10.85 0.03
## quarter 3 0.02 -1.35 0.07
## work_yrs 22 2.78 9.80 0.20
## frstlang 1 2.37 3.65 0.02
## salary 220000 0.70 -1.05 3078.10
## satis 997 1.77 1.13 22.45attach(mbasalary.df)Bar charts:
par(mfrow=c(1,2))
hist(mbasalary.df$age,
breaks=18,
col="gray",
xlab="age",
main="Histogram")
hist(mbasalary.df$sex,
breaks=18,
col="gray",
xlab="sex",
main="Histogram")
hist(mbasalary.df$gmat_tot,
breaks=18,
col="gray",
xlab="gmat_tot",
main="Histogram")
hist(mbasalary.df$gmat_qpc,
breaks=18,
col="gray",
xlab="gmat_qpc",
main="Histogram")
hist(mbasalary.df$gmat_vpc,
breaks=18,
col="gray",
xlab="gmat_vpc",
main="Histogram")
hist(mbasalary.df$gmat_tpc,
breaks=18,
col="gray",
xlab="gmat_tpc",
main="Histogram")
hist(mbasalary.df$s_avg,
breaks=18,
col="gray",
xlab="s_avg",
main="Histogram")
hist(mbasalary.df$f_avg,
breaks=18,
col="gray",
xlab="f_avg",
main="Histogram")
hist(mbasalary.df$quarter,
breaks=18,
col="gray",
xlab="quarter",
main="Histogram")
hist(mbasalary.df$work_yrs,
breaks=18,
col="gray",
xlab="work_yrs",
main="Histogram")
hist(mbasalary.df$frstlang,
breaks=18,
col="gray",
xlab="frstlang",
main="Histogram")
hist(mbasalary.df$salary,
breaks=18,
col="gray",
xlab="salary",
main="Histogram")
hist(mbasalary.df$satis,
breaks=18,
col="gray",
xlab="satis",
main="Histogram")
Boxplots :
par(mfrow=c(1,2))
boxplot(mbasalary.df$age)
boxplot(mbasalary.df$sex)
boxplot(mbasalary.df$gmat_tot)
boxplot(mbasalary.df$gmat_qpc)
boxplot(mbasalary.df$gmat_vpc)
boxplot(mbasalary.df$gmat_tpc)
boxplot(mbasalary.df$s_avg)
boxplot(mbasalary.df$f_avg)
boxplot(mbasalary.df$quarter)
boxplot(mbasalary.df$work_yrs)
boxplot(mbasalary.df$frstlang)
boxplot(mbasalary.df$salary)
boxplot(mbasalary.df$satis)
Scatterplot matrices:
library(car)##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logitpar(mfrow=c(1,1))
scatterplotMatrix(mbasalary.df[,c("age", "gmat_tot")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("age", "gmat_qpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("age", "gmat_tpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("age", "s_avg")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("age", "work_yrs")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("sex", "gmat_qpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="mediumblue")
scatterplotMatrix(mbasalary.df[,c("sex", "s_avg")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="mediumblue")
scatterplotMatrix(mbasalary.df[,c("gmat_tot", "gmat_qpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("gmat_tot", "gmat_vpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("gmat_tot", "gmat_vpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("gmat_tot", "work_yrs")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("gmat_qpc", "gmat_vpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcyan")
scatterplotMatrix(mbasalary.df[,c("gmat_qpc", "gmat_tpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcyan")
scatterplotMatrix(mbasalary.df[,c("gmat_qpc", "work_yrs")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcyan")
scatterplotMatrix(mbasalary.df[,c("gmat_qpc", "frstlang")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcyan")
scatterplotMatrix(mbasalary.df[,c("gmat_vpc", "gmat_tpc")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("gmat_vpc", "s_avg")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("gmat_vpc", "quarter")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("gmat_vpc", "frstlang")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("gmat_tpc", "work_yrs")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="mediumblue")
scatterplotMatrix(mbasalary.df[,c("s_avg", "f_avg")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("s_avg", "quarter")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("s_avg", "salary")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcoral")
scatterplotMatrix(mbasalary.df[,c("f_avg", "quarter")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcyan")
scatterplotMatrix(mbasalary.df[,c("quarter", "salary")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightpink")
scatterplotMatrix(mbasalary.df[,c("salary", "satis")],spread=FALSE, smoother.args=list(lty=2), main="Scatter Plot Matrix", col="lightcyan")
Corrgram:
library(corrgram)
corrgram(mbasalary.df, order=FALSE,
lower.panel=panel.shade,
upper.panel=panel.pie,
text.panel=panel.txt,
diag.panel=panel.minmax,
main="Corrgram")
Covariance Correlation Matrix:
#cov(mbasalary.df)
#cor(mbasalary.df)
#corr.test(mbasalary.df, use="complete")
library(corpcor)
library(tseries)
range.names = c("age", "sex", "gmat_tot", "gmat_qpc", "gmat_vpc", "gmat_tpc", "s_avg", "f_avg", "quarter", "work_yrs", "frstlang", "salary", "satis")
covmat = matrix(c(cov(mbasalary.df)), nrow=274, ncol=13)## Warning in matrix(c(cov(mbasalary.df)), nrow = 274, ncol = 13): data length
## [169] is not a sub-multiple or multiple of the number of rows [274]#names(range.names) = range.names
#dimnames(covmat) = list(names(range.names), range.names)
#covmatTASK 2b: WHO GOT HOW MUCH SALARY?
Take a subset of the dataset consisting of only those people who actually got a job. Using this subset of data: Think about the problem as y = f(x), where y = Starting Salary and x = various factors that it could depend upon
Examples: impact of {gender; first language; prior work experience; GMAT performance; MBA performance} etc in determining the Starting Salary
Draw Draw Contingency Tables, as appropriate Run chi-square tests, as appropriate Run t-tests, as appropriate Write more than one regression model as, as y = f(x) where the vector of variables x may be different in different models Estimate the regression models using lm() in R; Compare multiple models (e.g. using the R-Square measure given by lm()); Select the “best” model that “fits” the data;
Interpret the output
subsetone.df <- mbasalary.df[mbasalary.df[ , 12] != "0", ]
View(subsetone.df)
subsettwo.df<- subsetone.df[subsetone.df[ , 12] != "998", ]
View(subsettwo.df)
salariedmbas.df<- subsettwo.df[subsettwo.df[ , 12] != "999", ]
View(salariedmbas.df)Contingency Table:
library(vcd)## Loading required package: gridmytable <- xtabs(~ salary+sex, data=salariedmbas.df)
mytable## sex
## salary 1 2
## 64000 0 1
## 77000 1 0
## 78256 0 1
## 82000 0 1
## 85000 1 3
## 86000 0 2
## 88000 0 1
## 88500 1 0
## 90000 3 0
## 92000 2 1
## 93000 2 1
## 95000 4 3
## 96000 3 1
## 96500 1 0
## 97000 2 0
## 98000 6 4
## 99000 0 1
## 100000 4 5
## 100400 1 0
## 101000 0 2
## 101100 1 0
## 101600 1 0
## 102500 1 0
## 103000 1 0
## 104000 2 0
## 105000 11 0
## 106000 2 1
## 107000 1 0
## 107300 1 0
## 107500 1 0
## 108000 2 0
## 110000 0 1
## 112000 3 0
## 115000 5 0
## 118000 1 0
## 120000 3 1
## 126710 1 0
## 130000 1 0
## 145800 1 0
## 146000 1 0
## 162000 1 0
## 220000 0 1addmargins(mytable)## sex
## salary 1 2 Sum
## 64000 0 1 1
## 77000 1 0 1
## 78256 0 1 1
## 82000 0 1 1
## 85000 1 3 4
## 86000 0 2 2
## 88000 0 1 1
## 88500 1 0 1
## 90000 3 0 3
## 92000 2 1 3
## 93000 2 1 3
## 95000 4 3 7
## 96000 3 1 4
## 96500 1 0 1
## 97000 2 0 2
## 98000 6 4 10
## 99000 0 1 1
## 100000 4 5 9
## 100400 1 0 1
## 101000 0 2 2
## 101100 1 0 1
## 101600 1 0 1
## 102500 1 0 1
## 103000 1 0 1
## 104000 2 0 2
## 105000 11 0 11
## 106000 2 1 3
## 107000 1 0 1
## 107300 1 0 1
## 107500 1 0 1
## 108000 2 0 2
## 110000 0 1 1
## 112000 3 0 3
## 115000 5 0 5
## 118000 1 0 1
## 120000 3 1 4
## 126710 1 0 1
## 130000 1 0 1
## 145800 1 0 1
## 146000 1 0 1
## 162000 1 0 1
## 220000 0 1 1
## Sum 72 31 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 52.681, df = 41, p-value = 0.1045mytable <- xtabs(~ salary+frstlang, data=salariedmbas.df)
mytable## frstlang
## salary 1 2
## 64000 1 0
## 77000 1 0
## 78256 1 0
## 82000 1 0
## 85000 4 0
## 86000 2 0
## 88000 1 0
## 88500 1 0
## 90000 3 0
## 92000 3 0
## 93000 3 0
## 95000 7 0
## 96000 4 0
## 96500 1 0
## 97000 2 0
## 98000 8 2
## 99000 0 1
## 100000 9 0
## 100400 1 0
## 101000 2 0
## 101100 1 0
## 101600 1 0
## 102500 1 0
## 103000 1 0
## 104000 1 1
## 105000 11 0
## 106000 3 0
## 107000 1 0
## 107300 0 1
## 107500 1 0
## 108000 2 0
## 110000 1 0
## 112000 3 0
## 115000 5 0
## 118000 0 1
## 120000 4 0
## 126710 1 0
## 130000 1 0
## 145800 1 0
## 146000 1 0
## 162000 1 0
## 220000 0 1addmargins(mytable)## frstlang
## salary 1 2 Sum
## 64000 1 0 1
## 77000 1 0 1
## 78256 1 0 1
## 82000 1 0 1
## 85000 4 0 4
## 86000 2 0 2
## 88000 1 0 1
## 88500 1 0 1
## 90000 3 0 3
## 92000 3 0 3
## 93000 3 0 3
## 95000 7 0 7
## 96000 4 0 4
## 96500 1 0 1
## 97000 2 0 2
## 98000 8 2 10
## 99000 0 1 1
## 100000 9 0 9
## 100400 1 0 1
## 101000 2 0 2
## 101100 1 0 1
## 101600 1 0 1
## 102500 1 0 1
## 103000 1 0 1
## 104000 1 1 2
## 105000 11 0 11
## 106000 3 0 3
## 107000 1 0 1
## 107300 0 1 1
## 107500 1 0 1
## 108000 2 0 2
## 110000 1 0 1
## 112000 3 0 3
## 115000 5 0 5
## 118000 0 1 1
## 120000 4 0 4
## 126710 1 0 1
## 130000 1 0 1
## 145800 1 0 1
## 146000 1 0 1
## 162000 1 0 1
## 220000 0 1 1
## Sum 96 7 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 69.847, df = 41, p-value = 0.003296mytable <- xtabs(~ salary+work_yrs, data=salariedmbas.df)
mytable## work_yrs
## salary 0 1 2 3 4 5 6 7 8 10 15 16
## 64000 0 0 1 0 0 0 0 0 0 0 0 0
## 77000 0 0 1 0 0 0 0 0 0 0 0 0
## 78256 0 1 0 0 0 0 0 0 0 0 0 0
## 82000 0 1 0 0 0 0 0 0 0 0 0 0
## 85000 0 1 2 1 0 0 0 0 0 0 0 0
## 86000 0 0 1 1 0 0 0 0 0 0 0 0
## 88000 0 0 0 1 0 0 0 0 0 0 0 0
## 88500 0 0 0 1 0 0 0 0 0 0 0 0
## 90000 0 0 2 0 0 1 0 0 0 0 0 0
## 92000 0 0 3 0 0 0 0 0 0 0 0 0
## 93000 0 0 0 0 1 1 0 0 1 0 0 0
## 95000 1 1 2 2 0 1 0 0 0 0 0 0
## 96000 0 1 2 0 1 0 0 0 0 0 0 0
## 96500 0 0 1 0 0 0 0 0 0 0 0 0
## 97000 0 0 0 1 1 0 0 0 0 0 0 0
## 98000 0 0 7 1 1 0 0 1 0 0 0 0
## 99000 0 0 0 0 0 1 0 0 0 0 0 0
## 100000 0 0 6 1 1 0 1 0 0 0 0 0
## 100400 0 0 0 1 0 0 0 0 0 0 0 0
## 101000 0 0 2 0 0 0 0 0 0 0 0 0
## 101100 0 0 0 0 0 0 0 0 1 0 0 0
## 101600 0 0 0 1 0 0 0 0 0 0 0 0
## 102500 0 0 0 0 0 0 1 0 0 0 0 0
## 103000 0 0 0 1 0 0 0 0 0 0 0 0
## 104000 0 0 0 0 2 0 0 0 0 0 0 0
## 105000 0 0 4 4 0 1 1 0 0 0 0 1
## 106000 0 0 0 0 0 0 2 0 1 0 0 0
## 107000 0 0 1 0 0 0 0 0 0 0 0 0
## 107300 0 0 1 0 0 0 0 0 0 0 0 0
## 107500 0 0 0 1 0 0 0 0 0 0 0 0
## 108000 0 0 0 1 1 0 0 0 0 0 0 0
## 110000 0 0 0 0 0 0 1 0 0 0 0 0
## 112000 0 0 1 0 0 0 1 0 0 0 0 1
## 115000 0 2 0 1 2 0 0 0 0 0 0 0
## 118000 0 0 0 0 0 0 0 0 0 1 0 0
## 120000 0 0 0 1 0 2 0 0 1 0 0 0
## 126710 0 0 0 1 0 0 0 0 0 0 0 0
## 130000 0 0 0 0 1 0 0 0 0 0 0 0
## 145800 0 0 1 0 0 0 0 0 0 0 0 0
## 146000 0 0 0 0 0 0 0 0 0 0 1 0
## 162000 0 1 0 0 0 0 0 0 0 0 0 0
## 220000 0 0 0 0 0 0 0 0 0 0 1 0addmargins(mytable)## work_yrs
## salary 0 1 2 3 4 5 6 7 8 10 15 16 Sum
## 64000 0 0 1 0 0 0 0 0 0 0 0 0 1
## 77000 0 0 1 0 0 0 0 0 0 0 0 0 1
## 78256 0 1 0 0 0 0 0 0 0 0 0 0 1
## 82000 0 1 0 0 0 0 0 0 0 0 0 0 1
## 85000 0 1 2 1 0 0 0 0 0 0 0 0 4
## 86000 0 0 1 1 0 0 0 0 0 0 0 0 2
## 88000 0 0 0 1 0 0 0 0 0 0 0 0 1
## 88500 0 0 0 1 0 0 0 0 0 0 0 0 1
## 90000 0 0 2 0 0 1 0 0 0 0 0 0 3
## 92000 0 0 3 0 0 0 0 0 0 0 0 0 3
## 93000 0 0 0 0 1 1 0 0 1 0 0 0 3
## 95000 1 1 2 2 0 1 0 0 0 0 0 0 7
## 96000 0 1 2 0 1 0 0 0 0 0 0 0 4
## 96500 0 0 1 0 0 0 0 0 0 0 0 0 1
## 97000 0 0 0 1 1 0 0 0 0 0 0 0 2
## 98000 0 0 7 1 1 0 0 1 0 0 0 0 10
## 99000 0 0 0 0 0 1 0 0 0 0 0 0 1
## 100000 0 0 6 1 1 0 1 0 0 0 0 0 9
## 100400 0 0 0 1 0 0 0 0 0 0 0 0 1
## 101000 0 0 2 0 0 0 0 0 0 0 0 0 2
## 101100 0 0 0 0 0 0 0 0 1 0 0 0 1
## 101600 0 0 0 1 0 0 0 0 0 0 0 0 1
## 102500 0 0 0 0 0 0 1 0 0 0 0 0 1
## 103000 0 0 0 1 0 0 0 0 0 0 0 0 1
## 104000 0 0 0 0 2 0 0 0 0 0 0 0 2
## 105000 0 0 4 4 0 1 1 0 0 0 0 1 11
## 106000 0 0 0 0 0 0 2 0 1 0 0 0 3
## 107000 0 0 1 0 0 0 0 0 0 0 0 0 1
## 107300 0 0 1 0 0 0 0 0 0 0 0 0 1
## 107500 0 0 0 1 0 0 0 0 0 0 0 0 1
## 108000 0 0 0 1 1 0 0 0 0 0 0 0 2
## 110000 0 0 0 0 0 0 1 0 0 0 0 0 1
## 112000 0 0 1 0 0 0 1 0 0 0 0 1 3
## 115000 0 2 0 1 2 0 0 0 0 0 0 0 5
## 118000 0 0 0 0 0 0 0 0 0 1 0 0 1
## 120000 0 0 0 1 0 2 0 0 1 0 0 0 4
## 126710 0 0 0 1 0 0 0 0 0 0 0 0 1
## 130000 0 0 0 0 1 0 0 0 0 0 0 0 1
## 145800 0 0 1 0 0 0 0 0 0 0 0 0 1
## 146000 0 0 0 0 0 0 0 0 0 0 1 0 1
## 162000 0 1 0 0 0 0 0 0 0 0 0 0 1
## 220000 0 0 0 0 0 0 0 0 0 0 1 0 1
## Sum 1 8 38 21 11 7 7 1 4 1 2 2 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 535.23, df = 451, p-value = 0.003809mytable <- xtabs(~ salary+gmat_vpc, data=salariedmbas.df)
mytable## gmat_vpc
## salary 30 33 37 45 50 54 58 62 63 67 71 74 75 78 81 84 87 89 90 91 92 93
## 64000 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0
## 77000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 78256 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 82000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 85000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0
## 86000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 88000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
## 88500 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0
## 90000 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 0 0 0 1
## 92000 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0 0 0 0 0
## 93000 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0 0 0 0 0
## 95000 0 0 0 0 0 0 0 1 0 0 2 0 0 0 2 0 0 1 0 0 0 0
## 96000 0 0 0 0 0 0 0 1 0 0 0 0 0 0 1 0 0 1 0 0 0 1
## 96500 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 97000 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1 0 0 0 0 0
## 98000 0 0 1 0 0 0 1 1 0 1 1 0 0 0 1 0 0 0 1 1 0 0
## 99000 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 100000 0 0 0 0 1 0 0 0 0 1 1 0 0 1 1 2 1 0 0 0 1 0
## 100400 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 101000 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0
## 101100 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
## 101600 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0
## 102500 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 103000 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0
## 104000 0 0 0 1 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 105000 0 0 0 0 1 1 1 0 0 0 2 1 0 0 1 1 1 0 0 1 0 0
## 106000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0
## 107000 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 107300 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 107500 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
## 108000 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0 0 0
## 110000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 112000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0 0 1
## 115000 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 118000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
## 120000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 0
## 126710 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 130000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0
## 145800 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0
## 146000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 162000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1
## 220000 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## gmat_vpc
## salary 95 96 97 98 99
## 64000 0 0 0 0 0
## 77000 0 0 0 1 0
## 78256 0 0 0 0 0
## 82000 1 0 0 0 0
## 85000 0 0 0 2 0
## 86000 0 1 0 0 0
## 88000 0 0 0 0 0
## 88500 0 0 0 0 0
## 90000 0 0 0 0 0
## 92000 0 1 0 0 0
## 93000 0 0 0 1 0
## 95000 0 1 0 0 0
## 96000 0 0 0 0 0
## 96500 0 0 0 0 0
## 97000 0 0 0 0 0
## 98000 0 0 0 2 0
## 99000 0 0 0 0 0
## 100000 0 0 0 0 0
## 100400 1 0 0 0 0
## 101000 0 0 0 0 0
## 101100 0 0 0 0 0
## 101600 0 0 0 0 0
## 102500 0 0 1 0 0
## 103000 0 0 0 0 0
## 104000 0 0 0 0 0
## 105000 0 1 0 0 0
## 106000 0 1 0 0 1
## 107000 0 0 0 0 0
## 107300 1 0 0 0 0
## 107500 0 0 0 0 0
## 108000 0 0 0 0 0
## 110000 0 0 0 0 0
## 112000 0 0 0 0 0
## 115000 1 0 0 1 0
## 118000 0 0 0 0 0
## 120000 2 0 0 0 0
## 126710 0 0 0 0 0
## 130000 0 0 0 0 0
## 145800 0 0 0 0 0
## 146000 1 0 0 0 0
## 162000 0 0 0 0 0
## 220000 0 0 0 0 0addmargins(mytable)## gmat_vpc
## salary 30 33 37 45 50 54 58 62 63 67 71 74 75 78 81 84
## 64000 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
## 77000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 78256 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## 82000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 85000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 86000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## 88000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 88500 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
## 90000 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## 92000 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0
## 93000 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 0
## 95000 0 0 0 0 0 0 0 1 0 0 2 0 0 0 2 0
## 96000 0 0 0 0 0 0 0 1 0 0 0 0 0 0 1 0
## 96500 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 97000 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0
## 98000 0 0 1 0 0 0 1 1 0 1 1 0 0 0 1 0
## 99000 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
## 100000 0 0 0 0 1 0 0 0 0 1 1 0 0 1 1 2
## 100400 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 101000 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0 0
## 101100 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 101600 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0
## 102500 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 103000 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 104000 0 0 0 1 0 0 1 0 0 0 0 0 0 0 0 0
## 105000 0 0 0 0 1 1 1 0 0 0 2 1 0 0 1 1
## 106000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 107000 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## 107300 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 107500 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
## 108000 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1
## 110000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## 112000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## 115000 0 1 0 1 0 0 0 0 0 0 0 0 0 0 1 0
## 118000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 120000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1
## 126710 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
## 130000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 145800 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
## 146000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 162000 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 220000 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## Sum 1 1 1 3 2 1 5 4 1 6 9 7 1 2 11 5
## gmat_vpc
## salary 87 89 90 91 92 93 95 96 97 98 99 Sum
## 64000 0 0 0 0 0 0 0 0 0 0 0 1
## 77000 0 0 0 0 0 0 0 0 0 1 0 1
## 78256 0 0 0 0 0 0 0 0 0 0 0 1
## 82000 0 0 0 0 0 0 1 0 0 0 0 1
## 85000 1 0 0 0 1 0 0 0 0 2 0 4
## 86000 0 0 0 0 0 0 0 1 0 0 0 2
## 88000 0 0 0 1 0 0 0 0 0 0 0 1
## 88500 0 0 0 0 0 0 0 0 0 0 0 1
## 90000 0 1 0 0 0 1 0 0 0 0 0 3
## 92000 0 0 0 0 0 0 0 1 0 0 0 3
## 93000 0 0 0 0 0 0 0 0 0 1 0 3
## 95000 0 1 0 0 0 0 0 1 0 0 0 7
## 96000 0 1 0 0 0 1 0 0 0 0 0 4
## 96500 0 0 0 0 0 0 0 0 0 0 0 1
## 97000 1 0 0 0 0 0 0 0 0 0 0 2
## 98000 0 0 1 1 0 0 0 0 0 2 0 10
## 99000 0 0 0 0 0 0 0 0 0 0 0 1
## 100000 1 0 0 0 1 0 0 0 0 0 0 9
## 100400 0 0 0 0 0 0 1 0 0 0 0 1
## 101000 0 0 0 0 0 0 0 0 0 0 0 2
## 101100 0 0 1 0 0 0 0 0 0 0 0 1
## 101600 0 0 0 0 0 0 0 0 0 0 0 1
## 102500 0 0 0 0 0 0 0 0 1 0 0 1
## 103000 0 0 0 0 0 0 0 0 0 0 0 1
## 104000 0 0 0 0 0 0 0 0 0 0 0 2
## 105000 1 0 0 1 0 0 0 1 0 0 0 11
## 106000 1 0 0 0 0 0 0 1 0 0 1 3
## 107000 0 0 0 0 0 0 0 0 0 0 0 1
## 107300 0 0 0 0 0 0 1 0 0 0 0 1
## 107500 0 0 0 0 0 0 0 0 0 0 0 1
## 108000 0 0 0 0 0 0 0 0 0 0 0 2
## 110000 0 0 0 0 0 0 0 0 0 0 0 1
## 112000 1 0 0 0 0 1 0 0 0 0 0 3
## 115000 0 0 0 0 0 0 1 0 0 1 0 5
## 118000 0 1 0 0 0 0 0 0 0 0 0 1
## 120000 0 0 0 0 0 0 2 0 0 0 0 4
## 126710 0 0 0 0 0 0 0 0 0 0 0 1
## 130000 1 0 0 0 0 0 0 0 0 0 0 1
## 145800 0 0 0 0 0 0 0 0 0 0 0 1
## 146000 0 0 0 0 0 0 1 0 0 0 0 1
## 162000 0 0 0 0 0 1 0 0 0 0 0 1
## 220000 0 0 0 0 0 0 0 0 0 0 0 1
## Sum 7 4 2 3 2 4 7 5 1 7 1 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 1183.3, df = 1066, p-value = 0.006802mytable <- xtabs(~ salary+quarter, data=salariedmbas.df)
mytable## quarter
## salary 1 2 3 4
## 64000 0 0 0 1
## 77000 0 0 0 1
## 78256 0 0 1 0
## 82000 0 1 0 0
## 85000 2 0 0 2
## 86000 1 0 0 1
## 88000 1 0 0 0
## 88500 0 0 1 0
## 90000 0 0 2 1
## 92000 1 1 0 1
## 93000 1 1 1 0
## 95000 3 2 1 1
## 96000 2 1 0 1
## 96500 0 1 0 0
## 97000 0 0 2 0
## 98000 0 3 6 1
## 99000 0 1 0 0
## 100000 3 2 2 2
## 100400 0 0 0 1
## 101000 0 1 1 0
## 101100 0 0 1 0
## 101600 0 0 0 1
## 102500 0 0 1 0
## 103000 0 1 0 0
## 104000 0 1 0 1
## 105000 6 3 1 1
## 106000 2 0 1 0
## 107000 0 1 0 0
## 107300 0 0 1 0
## 107500 1 0 0 0
## 108000 1 0 1 0
## 110000 1 0 0 0
## 112000 1 1 1 0
## 115000 2 2 0 1
## 118000 1 0 0 0
## 120000 4 0 0 0
## 126710 0 0 0 1
## 130000 0 1 0 0
## 145800 0 1 0 0
## 146000 1 0 0 0
## 162000 1 0 0 0
## 220000 0 0 0 1addmargins(mytable)## quarter
## salary 1 2 3 4 Sum
## 64000 0 0 0 1 1
## 77000 0 0 0 1 1
## 78256 0 0 1 0 1
## 82000 0 1 0 0 1
## 85000 2 0 0 2 4
## 86000 1 0 0 1 2
## 88000 1 0 0 0 1
## 88500 0 0 1 0 1
## 90000 0 0 2 1 3
## 92000 1 1 0 1 3
## 93000 1 1 1 0 3
## 95000 3 2 1 1 7
## 96000 2 1 0 1 4
## 96500 0 1 0 0 1
## 97000 0 0 2 0 2
## 98000 0 3 6 1 10
## 99000 0 1 0 0 1
## 100000 3 2 2 2 9
## 100400 0 0 0 1 1
## 101000 0 1 1 0 2
## 101100 0 0 1 0 1
## 101600 0 0 0 1 1
## 102500 0 0 1 0 1
## 103000 0 1 0 0 1
## 104000 0 1 0 1 2
## 105000 6 3 1 1 11
## 106000 2 0 1 0 3
## 107000 0 1 0 0 1
## 107300 0 0 1 0 1
## 107500 1 0 0 0 1
## 108000 1 0 1 0 2
## 110000 1 0 0 0 1
## 112000 1 1 1 0 3
## 115000 2 2 0 1 5
## 118000 1 0 0 0 1
## 120000 4 0 0 0 4
## 126710 0 0 0 1 1
## 130000 0 1 0 0 1
## 145800 0 1 0 0 1
## 146000 1 0 0 0 1
## 162000 1 0 0 0 1
## 220000 0 0 0 1 1
## Sum 35 25 24 19 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 129.85, df = 123, p-value = 0.3186detach(mbasalary.df)
attach(salariedmbas.df)T tests:
library(MASS)
library(psych)
t.test(salariedmbas.df$salary ~ salariedmbas.df$sex, data=salariedmbas.df)##
## Welch Two Sample t-test
##
## data: salariedmbas.df$salary by salariedmbas.df$sex
## t = 1.3628, df = 38.115, p-value = 0.1809
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -3128.55 16021.72
## sample estimates:
## mean in group 1 mean in group 2
## 104970.97 98524.39t.test(salariedmbas.df$salary ~ salariedmbas.df$frstlang, data=salariedmbas.df)##
## Welch Two Sample t-test
##
## data: salariedmbas.df$salary by salariedmbas.df$frstlang
## t = -1.1202, df = 6.0863, p-value = 0.3049
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -59933.62 22202.25
## sample estimates:
## mean in group 1 mean in group 2
## 101748.6 120614.3t.test(salariedmbas.df$salary, salariedmbas.df$work_yrs, data=salariedmbas.df)##
## Welch Two Sample t-test
##
## data: salariedmbas.df$salary and salariedmbas.df$work_yrs
## t = 58.516, df = 102, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 99534.79 106519.33
## sample estimates:
## mean of x mean of y
## 1.030307e+05 3.679612e+00t.test(salariedmbas.df$salary, salariedmbas.df$gmat_vpc, data=salariedmbas.df)##
## Welch Two Sample t-test
##
## data: salariedmbas.df$salary and salariedmbas.df$gmat_vpc
## t = 58.473, df = 102, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 99459.9 106444.4
## sample estimates:
## mean of x mean of y
## 103030.73786 78.56311t.test(salariedmbas.df$salary, salariedmbas.df$quartile, data=salariedmbas.df)##
## One Sample t-test
##
## data: salariedmbas.df$salary
## t = 58.518, df = 102, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 99538.47 106523.01
## sample estimates:
## mean of x
## 103030.7detach(salariedmbas.df)
attach(mbasalary.df)Regression :
fit <-lm(salary ~ sex+frstlang+work_yrs+gmat_tpc+quarter)
summary(fit)##
## Call:
## lm(formula = salary ~ sex + frstlang + work_yrs + gmat_tpc +
## quarter)
##
## Residuals:
## Min 1Q Median 3Q Max
## -56018 -40660 -27819 54841 197132
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 67808.32 27048.48 2.507 0.0128 *
## sex 5693.06 7134.87 0.798 0.4256
## frstlang -11624.18 9603.28 -1.210 0.2272
## work_yrs -133.31 966.67 -0.138 0.8904
## gmat_tpc -59.63 223.76 -0.267 0.7901
## quarter -7009.23 2816.42 -2.489 0.0134 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 50530 on 268 degrees of freedom
## Multiple R-squared: 0.03463, Adjusted R-squared: 0.01662
## F-statistic: 1.923 on 5 and 268 DF, p-value: 0.0908fit$coefficients## (Intercept) sex frstlang work_yrs gmat_tpc
## 67808.31767 5693.05635 -11624.17549 -133.30707 -59.63415
## quarter
## -7009.23257salariedmbas.df$salary## [1] 85000 85000 86000 88000 92000 93000 95000 95000 95000 96000
## [11] 96000 100000 100000 100000 105000 105000 105000 105000 105000 105000
## [21] 106000 106000 107500 108000 110000 112000 115000 115000 118000 120000
## [31] 120000 120000 120000 146000 162000 82000 92000 93000 95000 95000
## [41] 96000 96500 98000 98000 98000 99000 100000 100000 101000 103000
## [51] 104000 105000 105000 105000 107000 112000 115000 115000 130000 145800
## [61] 78256 88500 90000 90000 93000 95000 97000 97000 98000 98000
## [71] 98000 98000 98000 98000 100000 100000 101000 101100 102500 105000
## [81] 106000 107300 108000 112000 64000 77000 85000 85000 86000 90000
## [91] 92000 95000 96000 98000 100000 100000 100400 101600 104000 105000
## [101] 115000 126710 220000fitted(fit)## 1 2 3 4 5 6 7 8
## 55106.24 49413.18 48936.11 50262.10 54450.26 49174.64 49413.18 54808.07
## 9 10 11 12 13 14 15 16
## 37669.74 48876.47 48697.57 55165.87 48623.90 48697.57 54422.18 54808.07
## 17 18 19 20 21 22 23 24
## 54362.55 37834.60 49293.91 49385.10 55435.96 48564.26 37206.70 56018.27
## 25 26 27 28 29 30 31 32
## 49816.58 49013.26 54934.29 48297.65 48508.11 54334.74 54439.70 55067.60
## 33 34 35 36 37 38 39 40
## 53282.05 47104.84 54822.10 54450.26 54569.53 54615.12 48757.20 54706.32
## 41 42 43 44 45 46 47 48
## 49202.72 56134.06 56523.42 49188.68 55197.43 54748.43 50367.33 48939.59
## 49 50 51 52 53 54 55 56
## 49055.38 50412.92 49995.48 49949.89 49251.80 49595.56 48613.34 54036.30
## 57 58 59 60 61 62 63 64
## 49041.34 49518.41 54334.47 47785.42 49862.18 48890.51 36722.55 49518.41
## 65 66 67 68 69 70 71 72
## 48357.28 49192.16 53829.32 47441.65 48890.51 42775.79 42105.78 32119.80
## 73 74 75 76 77 78 79 80
## 43119.56 42537.26 48619.67 41986.51 41807.61 41614.67 35936.12 41747.97
## 81 82 83 84 85 86 87 88
## 47784.79 30243.07 41807.61 41674.30 41926.87 42940.66 41674.30 48858.21
## 89 90 91 92 93 94 95 96
## 43165.15 32004.01 41688.34 41288.42 42628.45 42018.07 43031.85 38770.48
## 97 98 99 100 101 102 103 104
## 42018.07 47756.72 41600.63 42119.82 30930.60 43912.32 47665.53 41797.05
## 105 106 107 108 109 110 111 112
## 42228.52 42674.04 41600.63 41600.63 46956.87 42916.06 40891.97 48921.32
## 113 114 115 116 117 118 119 120
## 39913.23 40418.38 47753.24 48097.00 42916.06 41926.87 42330.28 43298.46
## 121 122 123 124 125 126 127 128
## 44491.14 42761.75 43119.56 37055.13 36549.98 48633.71 43031.85 48097.00
## 129 130 131 132 133 134 135 136
## 42211.01 43031.85 41733.93 42151.37 41611.06 42642.48 41393.65 42537.26
## 137 138 139 140 141 142 143 144
## 42018.07 41779.53 42403.95 34812.41 29165.43 34679.11 34858.01 40372.16
## 145 146 147 148 149 150 151 152
## 35170.22 35766.56 40849.24 35366.64 35275.45 36334.82 34872.05 34843.97
## 153 154 155 156 157 158 159 160
## 23517.96 24665.05 34591.39 23219.79 35082.51 34889.56 36022.61 36706.67
## 161 162 163 164 165 166 167 168
## 23742.46 41670.07 35321.04 35036.91 42027.88 34945.72 23563.56 40568.58
## 169 170 171 172 173 174 175 176
## 41522.73 29463.60 35499.94 34903.60 36289.23 35187.74 35440.31 38109.81
## 177 178 179 180 181 182 183 184
## 23146.12 40880.79 36548.76 23995.04 35962.98 35682.33 34254.59 34121.28
## 185 186 187 188 189 190 191 192
## 35233.21 42950.47 35261.41 35812.15 35275.45 35128.10 41582.36 35068.47
## 193 194 195 196 197 198 199 200
## 35798.12 40551.06 41982.28 41624.48 23174.20 35187.74 34012.57 34545.80
## 201 202 203 204 205 206 207 208
## 40968.50 41207.04 34117.80 34324.78 35931.42 34324.78 23353.10 35843.71
## 209 210 211 212 213 214 215 216
## 34798.37 28445.12 28280.25 28564.39 27669.87 33587.43 28280.25 28609.98
## 217 218 219 220 221 222 223 224
## 17119.11 27862.81 27908.41 31279.48 17522.51 28624.02 28967.79 28609.98
## 225 226 227 228 229 230 231 232
## 33468.16 27701.43 34913.42 27403.26 27880.33 29055.50 28399.52 27508.49
## 233 234 235 236 237 238 239 240
## 28788.88 28820.44 28252.18 27136.64 33173.73 29343.11 27122.61 28132.91
## 241 242 243 244 245 246 247 248
## 27775.10 16775.35 33275.22 28027.68 17434.80 21980.77 27599.68 28329.33
## 249 250 251 252 253 254 255 256
## 26870.03 29234.40 27420.78 17210.30 18329.31 28301.25 33022.64 35032.69
## 257 258 259 260 261 262 263 264
## 27908.41 33229.62 28266.21 33766.33 27627.76 27908.41 28445.12 28624.02
## 265 266 267 268 269 270 271 272
## 29101.09 34257.44 33720.73 28132.91 28013.64 17985.55 28922.19 29564.13
## 273 274
## 29325.59 22868.20residuals(fit)## 1 2 3 4 5 6 7
## -55106.24 -49413.18 -48936.11 -50262.10 -53451.26 -49174.64 -49413.18
## 8 9 10 11 12 13 14
## -54808.07 -36670.74 -47878.47 -47699.57 -54167.87 -47625.90 -47699.57
## 15 16 17 18 19 20 21
## -53424.18 -53810.07 -53364.55 -36836.60 -48295.91 -48387.10 -54436.96
## 22 23 24 25 26 27 28
## -48564.26 -37206.70 -56018.27 -49816.58 -48014.26 -54934.29 -48297.65
## 29 30 31 32 33 34 35
## -48508.11 -53335.74 -54439.70 -55067.60 -53282.05 -47104.84 30177.90
## 36 37 38 39 40 41 42
## 30549.74 31430.47 33384.88 43242.80 38293.68 45797.28 38865.94
## 43 44 45 46 47 48 49
## 38476.58 46811.32 40802.57 45251.57 49632.67 51060.41 55944.62
## 50 51 52 53 54 55 56
## 54587.08 55004.52 55050.11 55748.20 55404.44 57386.66 51963.70
## 57 58 59 60 61 62 63
## 58458.66 58481.59 55665.53 64214.58 65137.82 66109.49 81277.45
## 64 65 66 67 68 69 70
## 70481.59 71642.72 70807.84 66170.68 98558.35 113109.49 -42775.79
## 71 72 73 74 75 76 77
## -42105.78 -32119.80 -43119.56 -42537.26 -48619.67 -41986.51 -41807.61
## 78 79 80 81 82 83 84
## -40615.67 -34938.12 -40749.97 -46786.79 -29245.07 -40809.61 -40676.30
## 85 86 87 88 89 90 91
## -40928.87 -41942.66 -40675.30 -48858.21 -43165.15 -32004.01 -40689.34
## 92 93 94 95 96 97 98
## -41288.42 -42628.45 -41020.07 -42033.85 -37772.48 -42018.07 -47756.72
## 99 100 101 102 103 104 105
## -40601.63 -42119.82 -29931.60 -43912.32 -47665.53 -41797.05 -41229.52
## 106 107 108 109 110 111 112
## -42674.04 -41600.63 -40601.63 -46956.87 -42916.06 -40891.97 -48921.32
## 113 114 115 116 117 118 119
## -39913.23 -40418.38 34246.76 43903.00 50083.94 53073.13 52669.72
## 120 121 122 123 124 125 126
## 52701.54 52008.86 55238.25 54880.44 60944.87 62450.02 51366.29
## 127 128 129 130 131 132 133
## 56968.15 52903.00 60788.99 60968.15 63266.07 62848.63 63388.94
## 134 135 136 137 138 139 140
## 64357.52 70606.35 72462.74 72981.93 88220.47 103396.05 -34812.41
## 141 142 143 144 145 146 147
## -29165.43 -34679.11 -34858.01 -40372.16 -34171.22 -35766.56 -40849.24
## 148 149 150 151 152 153 154
## -34368.64 -34277.45 -36334.82 -34872.05 -33844.97 -22519.96 -23667.05
## 155 156 157 158 159 160 161
## -33593.39 -22221.79 -34084.51 -33890.56 -36022.61 -36706.67 -22743.46
## 162 163 164 165 166 167 168
## -41670.07 -35321.04 -35036.91 -42027.88 -33946.72 -23563.56 -40568.58
## 169 170 171 172 173 174 175
## -41522.73 -28464.60 -34501.94 -33905.60 -35291.23 -34189.74 -34442.31
## 176 177 178 179 180 181 182
## -37111.81 -22148.12 -39882.79 -35549.76 -23995.04 -34963.98 -35682.33
## 183 184 185 186 187 188 189
## -34254.59 -34121.28 -35233.21 35305.53 53238.59 54187.85 54724.55
## 190 191 192 193 194 195 196
## 57871.90 53417.64 61931.53 61201.88 57448.94 56017.72 56375.52
## 197 198 199 200 201 202 203
## 74825.80 62812.26 63987.43 65454.20 59031.50 59792.96 66982.20
## 204 205 206 207 208 209 210
## 68175.22 69068.58 71675.22 83946.90 72156.29 77201.63 -27447.12
## 211 212 213 214 215 216 217
## -27282.25 -27565.39 -27669.87 -32588.43 -27282.25 -27611.98 -16120.11
## 218 219 220 221 222 223 224
## -27862.81 -27908.41 -31279.48 -16523.51 -28624.02 -27968.79 -27611.98
## 225 226 227 228 229 230 231
## -32470.16 -26702.43 -34913.42 -26404.26 -27880.33 -29055.50 -27400.52
## 232 233 234 235 236 237 238
## -27508.49 -28788.88 -28820.44 -27253.18 -27136.64 -33173.73 -29343.11
## 239 240 241 242 243 244 245
## -26123.61 -27133.91 -27775.10 -16775.35 -33275.22 -28027.68 -16435.80
## 246 247 248 249 250 251 252
## -20981.77 -26601.68 -27331.33 -25872.03 -29234.40 -26421.78 -16211.30
## 253 254 255 256 257 258 259
## -18329.31 -28301.25 -33022.64 28967.31 49091.59 51770.38 56733.79
## 260 261 262 263 264 265 266
## 52233.67 62372.24 64091.59 66554.88 67375.98 68898.91 65742.56
## 267 268 269 270 271 272 273
## 66279.27 72267.09 73586.36 86014.45 76077.81 85435.87 97384.41
## 274
## 197131.80Plots:
par(mfrow=c(1,2))
plot(salariedmbas.df$salary,salariedmbas.df$sex,main="Plot 1",xlab="Salary",ylab="Sex")
plot(salariedmbas.df$salary,salariedmbas.df$frstlang,main="Plot 2",xlab="Salary",ylab="First language") 
plot(salariedmbas.df$salary,salariedmbas.df$work_yrs,main="Plot 3",xlab="Salary",ylab="Work exp")
plot(salariedmbas.df$salary,salariedmbas.df$gmat_tpc,main="Plot 4",xlab="Salary",ylab="GMAT Percentile") 
plot(salariedmbas.df$salary,salariedmbas.df$quarter,main="Plot 5",xlab="Salary",ylab="Quarter")
plot(salariedmbas.df$salary,salariedmbas.df$gmat_tot,main="Plot 6",xlab="Salary",ylab="GMAT Total") 
plot(salariedmbas.df$salary,salariedmbas.df$age,main="Plot 7",xlab="Salary",ylab="age") 
Salary == 0 (Jobless)
joblessmbas.df <- mbasalary.df[mbasalary.df[ , 12] == "0", ]
View(joblessmbas.df)Contingency tables :
mytable <- xtabs(~ gmat_vpc+quarter, data=salariedmbas.df)
mytable## quarter
## gmat_vpc 1 2 3 4
## 30 0 1 0 0
## 33 1 0 0 0
## 37 0 1 0 0
## 45 0 0 0 3
## 50 2 0 0 0
## 54 0 0 1 0
## 58 0 4 0 1
## 62 1 1 0 2
## 63 0 1 0 0
## 67 0 2 4 0
## 71 2 2 3 2
## 74 2 3 2 0
## 75 1 0 0 0
## 78 0 0 0 2
## 81 5 3 0 3
## 84 3 0 1 1
## 87 1 2 3 1
## 89 2 1 0 1
## 90 0 0 2 0
## 91 2 0 1 0
## 92 1 0 1 0
## 93 2 1 1 0
## 95 3 2 1 1
## 96 4 1 0 0
## 97 0 0 1 0
## 98 3 0 2 2
## 99 0 0 1 0addmargins(mytable)## quarter
## gmat_vpc 1 2 3 4 Sum
## 30 0 1 0 0 1
## 33 1 0 0 0 1
## 37 0 1 0 0 1
## 45 0 0 0 3 3
## 50 2 0 0 0 2
## 54 0 0 1 0 1
## 58 0 4 0 1 5
## 62 1 1 0 2 4
## 63 0 1 0 0 1
## 67 0 2 4 0 6
## 71 2 2 3 2 9
## 74 2 3 2 0 7
## 75 1 0 0 0 1
## 78 0 0 0 2 2
## 81 5 3 0 3 11
## 84 3 0 1 1 5
## 87 1 2 3 1 7
## 89 2 1 0 1 4
## 90 0 0 2 0 2
## 91 2 0 1 0 3
## 92 1 0 1 0 2
## 93 2 1 1 0 4
## 95 3 2 1 1 7
## 96 4 1 0 0 5
## 97 0 0 1 0 1
## 98 3 0 2 2 7
## 99 0 0 1 0 1
## Sum 35 25 24 19 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 101.86, df = 78, p-value = 0.03621mytable <- xtabs(~ gmat_vpc+work_yrs, data=salariedmbas.df)
mytable## work_yrs
## gmat_vpc 0 1 2 3 4 5 6 7 8 10 15 16
## 30 0 0 1 0 0 0 0 0 0 0 0 0
## 33 0 0 0 0 1 0 0 0 0 0 0 0
## 37 0 0 0 1 0 0 0 0 0 0 0 0
## 45 0 0 0 1 1 0 0 0 0 0 1 0
## 50 0 0 1 1 0 0 0 0 0 0 0 0
## 54 0 0 1 0 0 0 0 0 0 0 0 0
## 58 0 0 1 1 1 1 0 0 0 0 0 1
## 62 0 0 2 1 0 0 0 0 1 0 0 0
## 63 0 0 0 1 0 0 0 0 0 0 0 0
## 67 0 1 3 0 2 0 0 0 0 0 0 0
## 71 0 0 4 3 0 1 1 0 0 0 0 0
## 74 0 0 3 3 1 0 0 0 0 0 0 0
## 75 0 0 0 1 0 0 0 0 0 0 0 0
## 78 0 0 2 0 0 0 0 0 0 0 0 0
## 81 0 2 5 1 0 1 1 0 0 0 0 1
## 84 0 0 2 1 1 0 1 0 0 0 0 0
## 87 0 0 3 1 2 0 1 0 0 0 0 0
## 89 0 0 1 0 1 1 0 0 0 1 0 0
## 90 0 0 1 0 0 0 0 0 1 0 0 0
## 91 0 0 1 1 0 1 0 0 0 0 0 0
## 92 0 1 0 1 0 0 0 0 0 0 0 0
## 93 0 2 1 0 0 0 1 0 0 0 0 0
## 95 0 1 1 1 1 1 0 0 1 0 1 0
## 96 1 0 2 1 0 0 0 0 1 0 0 0
## 97 0 0 0 0 0 0 1 0 0 0 0 0
## 98 0 1 3 1 0 1 0 1 0 0 0 0
## 99 0 0 0 0 0 0 1 0 0 0 0 0addmargins(mytable)## work_yrs
## gmat_vpc 0 1 2 3 4 5 6 7 8 10 15 16 Sum
## 30 0 0 1 0 0 0 0 0 0 0 0 0 1
## 33 0 0 0 0 1 0 0 0 0 0 0 0 1
## 37 0 0 0 1 0 0 0 0 0 0 0 0 1
## 45 0 0 0 1 1 0 0 0 0 0 1 0 3
## 50 0 0 1 1 0 0 0 0 0 0 0 0 2
## 54 0 0 1 0 0 0 0 0 0 0 0 0 1
## 58 0 0 1 1 1 1 0 0 0 0 0 1 5
## 62 0 0 2 1 0 0 0 0 1 0 0 0 4
## 63 0 0 0 1 0 0 0 0 0 0 0 0 1
## 67 0 1 3 0 2 0 0 0 0 0 0 0 6
## 71 0 0 4 3 0 1 1 0 0 0 0 0 9
## 74 0 0 3 3 1 0 0 0 0 0 0 0 7
## 75 0 0 0 1 0 0 0 0 0 0 0 0 1
## 78 0 0 2 0 0 0 0 0 0 0 0 0 2
## 81 0 2 5 1 0 1 1 0 0 0 0 1 11
## 84 0 0 2 1 1 0 1 0 0 0 0 0 5
## 87 0 0 3 1 2 0 1 0 0 0 0 0 7
## 89 0 0 1 0 1 1 0 0 0 1 0 0 4
## 90 0 0 1 0 0 0 0 0 1 0 0 0 2
## 91 0 0 1 1 0 1 0 0 0 0 0 0 3
## 92 0 1 0 1 0 0 0 0 0 0 0 0 2
## 93 0 2 1 0 0 0 1 0 0 0 0 0 4
## 95 0 1 1 1 1 1 0 0 1 0 1 0 7
## 96 1 0 2 1 0 0 0 0 1 0 0 0 5
## 97 0 0 0 0 0 0 1 0 0 0 0 0 1
## 98 0 1 3 1 0 1 0 1 0 0 0 0 7
## 99 0 0 0 0 0 0 1 0 0 0 0 0 1
## Sum 1 8 38 21 11 7 7 1 4 1 2 2 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 238.3, df = 286, p-value = 0.9817mytable <- xtabs(~ work_yrs+quarter, data=salariedmbas.df)
mytable## quarter
## work_yrs 1 2 3 4
## 0 1 0 0 0
## 1 5 2 1 0
## 2 7 10 11 10
## 3 7 5 3 6
## 4 2 4 4 1
## 5 4 1 1 1
## 6 4 1 2 0
## 7 0 0 1 0
## 8 2 1 1 0
## 10 1 0 0 0
## 15 1 0 0 1
## 16 1 1 0 0addmargins(mytable)## quarter
## work_yrs 1 2 3 4 Sum
## 0 1 0 0 0 1
## 1 5 2 1 0 8
## 2 7 10 11 10 38
## 3 7 5 3 6 21
## 4 2 4 4 1 11
## 5 4 1 1 1 7
## 6 4 1 2 0 7
## 7 0 0 1 0 1
## 8 2 1 1 0 4
## 10 1 0 0 0 1
## 15 1 0 0 1 2
## 16 1 1 0 0 2
## Sum 35 25 24 19 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 29.47, df = 33, p-value = 0.6436mytable <- xtabs(~ work_yrs+age, data=salariedmbas.df)
mytable## age
## work_yrs 22 23 24 25 26 27 28 29 30 31 32 33 34 39 40
## 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 1 1 1 1 3 1 1 0 0 0 0 0 0 0 0 0
## 2 0 4 13 12 5 3 0 0 0 0 1 0 0 0 0
## 3 0 0 1 7 6 5 1 1 0 0 0 0 0 0 0
## 4 0 0 0 1 2 3 3 0 0 2 0 0 0 0 0
## 5 0 0 0 0 0 1 3 1 2 0 0 0 0 0 0
## 6 0 0 0 0 0 1 1 2 2 1 0 0 0 0 0
## 7 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 8 0 0 0 0 0 0 0 1 2 1 0 0 0 0 0
## 10 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
## 15 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2
## 16 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0addmargins(mytable)## age
## work_yrs 22 23 24 25 26 27 28 29 30 31 32 33 34 39 40 Sum
## 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 1
## 1 1 1 1 3 1 1 0 0 0 0 0 0 0 0 0 8
## 2 0 4 13 12 5 3 0 0 0 0 1 0 0 0 0 38
## 3 0 0 1 7 6 5 1 1 0 0 0 0 0 0 0 21
## 4 0 0 0 1 2 3 3 0 0 2 0 0 0 0 0 11
## 5 0 0 0 0 0 1 3 1 2 0 0 0 0 0 0 7
## 6 0 0 0 0 0 1 1 2 2 1 0 0 0 0 0 7
## 7 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1
## 8 0 0 0 0 0 0 0 1 2 1 0 0 0 0 0 4
## 10 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 1
## 15 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 2
## 16 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 2
## Sum 1 5 16 23 14 14 8 6 6 4 1 1 1 1 2 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 462.81, df = 154, p-value < 2.2e-16mytable <- xtabs(~ sex+gmat_vpc, data=salariedmbas.df)
mytable## gmat_vpc
## sex 30 33 37 45 50 54 58 62 63 67 71 74 75 78 81 84 87 89 90 91 92 93 95
## 1 1 1 0 2 2 1 4 3 1 4 6 5 1 0 7 4 5 3 2 1 1 4 5
## 2 0 0 1 1 0 0 1 1 0 2 3 2 0 2 4 1 2 1 0 2 1 0 2
## gmat_vpc
## sex 96 97 98 99
## 1 4 1 3 1
## 2 1 0 4 0addmargins(mytable)## gmat_vpc
## sex 30 33 37 45 50 54 58 62 63 67 71 74 75 78 81 84 87
## 1 1 1 0 2 2 1 4 3 1 4 6 5 1 0 7 4 5
## 2 0 0 1 1 0 0 1 1 0 2 3 2 0 2 4 1 2
## Sum 1 1 1 3 2 1 5 4 1 6 9 7 1 2 11 5 7
## gmat_vpc
## sex 89 90 91 92 93 95 96 97 98 99 Sum
## 1 3 2 1 1 4 5 4 1 3 1 72
## 2 1 0 2 1 0 2 1 0 4 0 31
## Sum 4 2 3 2 4 7 5 1 7 1 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 19.287, df = 26, p-value = 0.8241mytable <- xtabs(~ work_yrs+quarter, data=salariedmbas.df)
mytable## quarter
## work_yrs 1 2 3 4
## 0 1 0 0 0
## 1 5 2 1 0
## 2 7 10 11 10
## 3 7 5 3 6
## 4 2 4 4 1
## 5 4 1 1 1
## 6 4 1 2 0
## 7 0 0 1 0
## 8 2 1 1 0
## 10 1 0 0 0
## 15 1 0 0 1
## 16 1 1 0 0addmargins(mytable)## quarter
## work_yrs 1 2 3 4 Sum
## 0 1 0 0 0 1
## 1 5 2 1 0 8
## 2 7 10 11 10 38
## 3 7 5 3 6 21
## 4 2 4 4 1 11
## 5 4 1 1 1 7
## 6 4 1 2 0 7
## 7 0 0 1 0 1
## 8 2 1 1 0 4
## 10 1 0 0 0 1
## 15 1 0 0 1 2
## 16 1 1 0 0 2
## Sum 35 25 24 19 103chisq.test(mytable)## Warning in chisq.test(mytable): Chi-squared approximation may be incorrect##
## Pearson's Chi-squared test
##
## data: mytable
## X-squared = 29.47, df = 33, p-value = 0.6436Linear Model Regression:
salarymention <- mbasalary.df[which(mbasalary.df$salary!='998' && mbasalary.df$salary!='999'),]
salarymention$salary[salarymention$salary>0] = 1
salarymention$salary[salarymention$salary < 1] = 0
library(ROCR)## Loading required package: gplots##
## Attaching package: 'gplots'## The following object is masked from 'package:stats':
##
## lowesstrain=salarymention[1:96,]
test=salarymention[97:193,]
formula=salary~age+sex+work_yrs+frstlang+gmat_tot+gmat_qpc+gmat_vpc+gmat_tpc+f_avg+s_avg+quarter+frstlang+satis
x=glm(formula = formula, family = binomial(link = "logit"), data = train)
summary(x)##
## Call:
## glm(formula = formula, family = binomial(link = "logit"), data = train)
##
## Deviance Residuals:
## [1] 0
##
## Coefficients: (12 not defined because of singularities)
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -22.57 48196.14 0 1
## age NA NA NA NA
## sex NA NA NA NA
## work_yrs NA NA NA NA
## frstlang NA NA NA NA
## gmat_tot NA NA NA NA
## gmat_qpc NA NA NA NA
## gmat_vpc NA NA NA NA
## gmat_tpc NA NA NA NA
## f_avg NA NA NA NA
## s_avg NA NA NA NA
## quarter NA NA NA NA
## satis NA NA NA NA
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 0.0000e+00 on 0 degrees of freedom
## Residual deviance: 3.1675e-10 on 0 degrees of freedom
## (95 observations deleted due to missingness)
## AIC: 2
##
## Number of Fisher Scoring iterations: 21anova(x, test = "Chisq")## Analysis of Deviance Table
##
## Model: binomial, link: logit
##
## Response: salary
##
## Terms added sequentially (first to last)
##
##
## Df Deviance Resid. Df Resid. Dev Pr(>Chi)
## NULL 0 0.0000e+00
## age 0 0 0 3.1675e-10
## sex 0 0 0 3.1675e-10
## work_yrs 0 0 0 3.1675e-10
## frstlang 0 0 0 3.1675e-10
## gmat_tot 0 0 0 3.1675e-10
## gmat_qpc 0 0 0 3.1675e-10
## gmat_vpc 0 0 0 3.1675e-10
## gmat_tpc 0 0 0 3.1675e-10
## f_avg 0 0 0 3.1675e-10
## s_avg 0 0 0 3.1675e-10
## quarter 0 0 0 3.1675e-10
## satis 0 0 0 3.1675e-10Observation: Salary depends on Work Experience, GMAT Total, GMAT Percentile and Age.