MBA Starting Salaries
NarasingaMoorthy V
February 21, 2018
setwd("C:/Office/Week 4 Day 2")MBAStartingSalariesData.df <- read.csv(paste("MBA Starting Salaries Data.csv"),sep = ",")
View(MBAStartingSalariesData.df)summary(MBAStartingSalariesData.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. :998.0boxplot(MBAStartingSalariesData.df$gmat_tot~MBAStartingSalariesData.df$sex)
hist(MBAStartingSalariesData.df$salary)
plot(MBAStartingSalariesData.df$age, MBAStartingSalariesData.df$salary)
var(MBAStartingSalariesData.df)## age sex gmat_tot gmat_qpc
## age 1.376904e+01 -4.513248e-02 -3.115879e+01 -1.192655e+01
## sex -4.513248e-02 1.872677e-01 -1.328841e+00 -1.053769e+00
## gmat_tot -3.115879e+01 -1.328841e+00 3.310688e+03 6.200233e+02
## gmat_qpc -1.192655e+01 -1.053769e+00 6.200233e+02 2.210731e+02
## gmat_vpc -2.763643e+00 5.463758e-01 7.260006e+02 3.814826e+01
## gmat_tpc -8.839978e+00 -4.908960e-02 6.839911e+02 1.357997e+02
## s_avg 2.116874e-01 2.096227e-02 2.480257e+00 -1.691233e-01
## f_avg -3.399348e-02 2.082698e-02 3.154688e+00 5.753854e-01
## quarter -2.045935e-01 -6.414267e-02 -5.891153e+00 6.001979e-01
## work_yrs 1.029494e+01 -1.580172e-02 -3.391634e+01 -1.137186e+01
## frstlang 6.796610e-02 2.138980e-04 -2.499933e+00 6.646346e-01
## salary -1.183042e+04 1.518264e+03 -1.611600e+05 -3.335823e+04
## satis -1.763499e+02 -8.780808e+00 1.765263e+03 3.348371e+02
## gmat_vpc gmat_tpc s_avg f_avg
## age -2.7636427 -8.8399775 0.21168739 -0.03399348
## sex 0.5463758 -0.0490896 0.02096227 0.02082698
## gmat_tot 726.0006417 683.9910698 2.48025721 3.15468838
## gmat_qpc 38.1482581 135.7996845 -0.16912329 0.57538542
## gmat_vpc 284.2481217 157.4932488 1.31357023 0.67207000
## gmat_tpc 157.4932488 196.6057057 0.62710008 0.58698618
## s_avg 1.3135702 0.6271001 0.14521760 0.11016898
## f_avg 0.6720700 0.5869862 0.11016898 0.27567237
## quarter -3.2676666 -1.2923719 -0.32237213 -0.26080880
## work_yrs -3.6181653 -7.8575172 0.15926392 -0.06628700
## frstlang -2.1145691 -0.4663244 -0.01671372 -0.00626026
## salary -5273.8523836 3522.7500067 2831.60098580 787.65597177
## satis 392.3562739 484.2466779 -4.62884495 2.12532927
## quarter work_yrs frstlang salary
## age -2.045935e-01 10.29493864 6.796610e-02 -1.183042e+04
## sex -6.414267e-02 -0.01580172 2.138980e-04 1.518264e+03
## gmat_tot -5.891153e+00 -33.91633914 -2.499933e+00 -1.611600e+05
## gmat_qpc 6.001979e-01 -11.37186171 6.646346e-01 -3.335823e+04
## gmat_vpc -3.267667e+00 -3.61816529 -2.114569e+00 -5.273852e+03
## gmat_tpc -1.292372e+00 -7.85751718 -4.663244e-01 3.522750e+03
## s_avg -3.223721e-01 0.15926392 -1.671372e-02 2.831601e+03
## f_avg -2.608088e-01 -0.06628700 -6.260260e-03 7.876560e+02
## quarter 1.232119e+00 -0.30866822 3.553381e-02 -9.296214e+03
## work_yrs -3.086682e-01 10.44882490 -2.898318e-02 1.486147e+03
## frstlang 3.553381e-02 -0.02898318 1.035266e-01 -1.419586e+03
## salary -9.296214e+03 1486.14704152 -1.419586e+03 2.596062e+09
## satis -5.227133e-03 -131.24080907 9.484532e+00 -6.347115e+06
## satis
## age -1.763499e+02
## sex -8.780808e+00
## gmat_tot 1.765263e+03
## gmat_qpc 3.348371e+02
## gmat_vpc 3.923563e+02
## gmat_tpc 4.842467e+02
## s_avg -4.628845e+00
## f_avg 2.125329e+00
## quarter -5.227133e-03
## work_yrs -1.312408e+02
## frstlang 9.484532e+00
## salary -6.347115e+06
## satis 1.380974e+05library(corrgram)
corrgram(MBAStartingSalariesData.df, order=TRUE, lower.panel=panel.shade,
upper.panel=panel.pie,)
MBAStartingSalaries.df = placed.df+notplaced.df + undisclosedsalary.df +SurveyNotAnswered.df
placed.df <- MBAStartingSalariesData.df[which(MBAStartingSalariesData.df$salary >999),]notplaced.df<- MBAStartingSalariesData.df[which(MBAStartingSalariesData.df$salary==0), ]undisclosedsalary.df<- MBAStartingSalariesData.df[which(MBAStartingSalariesData.df$salary==999),]SurveyNotAnswered.df<- MBAStartingSalariesData.df[which(MBAStartingSalariesData.df$salary==998),]View(placed.df)
View(notplaced.df)
View(undisclosedsalary.df)
View(SurveyNotAnswered.df)MBAStartingSalaries.df = placed.df+notplaced.df + undisclosedsalary.df +SurveyNotAnswered.df
table(placed.df$sex, placed.df$salary)##
## 64000 77000 78256 82000 85000 86000 88000 88500 90000 92000 93000
## 1 0 1 0 0 1 0 0 1 3 2 2
## 2 1 0 1 1 3 2 1 0 0 1 1
##
## 95000 96000 96500 97000 98000 99000 100000 100400 101000 101100 101600
## 1 4 3 1 2 6 0 4 1 0 1 1
## 2 3 1 0 0 4 1 5 0 2 0 0
##
## 102500 103000 104000 105000 106000 107000 107300 107500 108000 110000
## 1 1 1 2 11 2 1 1 1 2 0
## 2 0 0 0 0 1 0 0 0 0 1
##
## 112000 115000 118000 120000 126710 130000 145800 146000 162000 220000
## 1 3 5 1 3 1 1 1 1 1 0
## 2 0 0 0 1 0 0 0 0 0 1chisq.test(placed.df)## Warning in chisq.test(placed.df): Chi-squared approximation may be
## incorrect##
## Pearson's Chi-squared test
##
## data: placed.df
## X-squared = 3620.8, df = 1224, p-value < 2.2e-16t.test(placed.df)##
## One Sample t-test
##
## data: placed.df
## t = 10.492, df = 1338, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
## 6500.198 9490.068
## sample estimates:
## mean of x
## 7995.133Model1 <- salary ~
work_yrs + s_avg + f_avg + gmat_qpc + gmat_vpc + sex + frstlang + satisbestmodel <- lm(Model1, data = placed.df)summary(bestmodel)##
## Call:
## lm(formula = Model1, data = placed.df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -29800 -7822 -1742 4869 82341
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 86719.94 23350.43 3.714 0.000346 ***
## work_yrs 2331.12 585.99 3.978 0.000137 ***
## s_avg 4659.05 5015.66 0.929 0.355320
## f_avg -1698.83 3834.70 -0.443 0.658773
## gmat_qpc 98.72 121.85 0.810 0.419884
## gmat_vpc -95.80 102.99 -0.930 0.354699
## sex -5289.24 3545.91 -1.492 0.139140
## frstlang 13994.76 6641.66 2.107 0.037770 *
## satis -1671.20 2070.62 -0.807 0.421643
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 15740 on 94 degrees of freedom
## Multiple R-squared: 0.285, Adjusted R-squared: 0.2241
## F-statistic: 4.683 on 8 and 94 DF, p-value: 7.574e-05