-----------------MBA-Starting salaries Harvard business case study Analysis under guidance OF PROF.SAMEER
MATHUR(PH.D) IIM-LUCKNOW.-----------------------
##reading the data into R
mbasal <- read.csv(paste( "MBA Starting Salaries Data.csv" ,sep=""))
##viewing the data.
library(psych)
View(mbasal)
##describing the data.
describe(mbasal)
## 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 22.45
##summary the data.
summary(mbasal)
## 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. :998.0
##describing the dataset
str(mbasal)
## 'data.frame': 274 obs. of 13 variables:
## $ age : int 23 24 24 24 24 24 25 25 25 25 ...
## $ sex : int 2 1 1 1 2 1 1 2 1 1 ...
## $ gmat_tot: int 620 610 670 570 710 640 610 650 630 680 ...
## $ gmat_qpc: int 77 90 99 56 93 82 89 88 79 99 ...
## $ gmat_vpc: int 87 71 78 81 98 89 74 89 91 81 ...
## $ gmat_tpc: int 87 87 95 75 98 91 87 92 89 96 ...
## $ s_avg : num 3.4 3.5 3.3 3.3 3.6 3.9 3.4 3.3 3.3 3.45 ...
## $ f_avg : num 3 4 3.25 2.67 3.75 3.75 3.5 3.75 3.25 3.67 ...
## $ quarter : int 1 1 1 1 1 1 1 1 1 1 ...
## $ work_yrs: int 2 2 2 1 2 2 2 2 2 2 ...
## $ frstlang: int 1 1 1 1 1 1 1 1 2 1 ...
## $ salary : int 0 0 0 0 999 0 0 0 999 998 ...
## $ satis : int 7 6 6 7 5 6 5 6 4 998 ...
--------------------Boxplot illustrations---------------------
------------------Histogram illustrations---------------------
------------------Scatter plots construction------------------------
##
## Attaching package: 'car'
## The following object is masked from 'package:psych':
##
## logit
------------------corrgram construction-----------------------------
##covariance
cov(mbasal)
## 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+05
##creating a dataset of the students who actually got the job
mba=mbasal[which(mbasal$salary!=0),]
View(mba)
##creating tables.
table(mba$s_avg,mba$f_avg)
##
## 0 2 2.25 2.33 2.5 2.67 2.75 2.8 2.83 3 3.17 3.2 3.25 3.33 3.4 3.5
## 2.2 0 1 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## 2.3 0 0 1 0 1 0 0 0 0 0 0 0 0 0 0 0
## 2.4 0 1 1 0 2 0 3 0 0 0 0 0 0 0 0 0
## 2.45 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0
## 2.5 0 0 1 0 3 0 4 0 0 2 0 0 0 0 0 0
## 2.6 0 0 0 0 4 0 3 0 0 3 0 0 0 0 0 0
## 2.67 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 2.7 0 0 0 0 3 0 6 0 0 6 0 1 3 0 0 0
## 2.73 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0
## 2.8 0 0 0 0 0 0 3 0 0 5 0 0 2 0 0 0
## 2.9 0 0 0 0 0 0 5 1 0 6 0 0 6 1 0 1
## 2.91 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 3 0 0 0 0 0 0 4 0 0 6 0 0 4 0 0 0
## 3.09 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1
## 3.1 0 0 0 1 0 1 0 0 0 5 0 0 2 1 0 3
## 3.18 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
## 3.2 0 0 0 0 0 0 0 0 0 4 0 0 6 0 1 1
## 3.27 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
## 3.3 0 0 0 0 0 0 0 0 0 2 0 0 9 0 0 5
## 3.4 0 0 0 0 0 0 0 1 0 1 0 0 3 0 0 0
## 3.45 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1
## 3.5 0 0 0 0 0 1 0 0 0 2 0 0 3 0 0 4
## 3.56 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 3.6 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 4
## 3.7 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 3.8 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2
## 4 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
##
## 3.6 3.67 3.75 4
## 2.2 0 0 0 0
## 2.3 0 0 0 0
## 2.4 0 0 0 0
## 2.45 0 0 0 0
## 2.5 0 0 0 0
## 2.6 0 0 0 0
## 2.67 0 0 0 0
## 2.7 0 0 0 0
## 2.73 0 0 0 0
## 2.8 0 0 0 0
## 2.9 0 0 0 0
## 2.91 0 0 0 0
## 3 0 0 0 0
## 3.09 0 0 0 0
## 3.1 0 0 1 0
## 3.18 0 0 0 0
## 3.2 0 0 0 0
## 3.27 0 0 0 0
## 3.3 0 0 0 0
## 3.4 0 1 2 1
## 3.45 0 1 0 0
## 3.5 1 0 1 2
## 3.56 0 0 0 1
## 3.6 0 1 2 0
## 3.7 1 0 0 1
## 3.8 0 0 0 1
## 4 0 0 0 1
##creating tables.
table(mba$gmat_tot,mba$gmat_qpc)
##
## 39 43 46 48 49 50 52 53 55 56 57 60 64 65 66 67 68 71 72 74 75 77 78
## 450 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 460 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0
## 500 0 0 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 1
## 520 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 530 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
## 540 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0
## 550 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 1 0 0 0
## 560 1 0 0 0 0 0 3 0 1 0 1 1 1 0 0 0 1 0 0 0 1 0 0
## 570 0 0 0 0 0 0 0 0 0 1 0 0 0 1 0 0 1 1 1 0 1 0 0
## 580 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 3 0 0 0 1
## 590 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 2 0 1 0 0 0 0
## 600 0 0 0 0 0 0 0 1 0 0 0 1 0 0 0 1 1 0 1 0 0 4 0
## 610 0 0 0 1 0 0 0 0 0 0 0 0 1 0 0 0 0 0 1 0 1 0 0
## 620 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0 0 0 0 1 0 0 0 1
## 630 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 2 0 1 0 0
## 640 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 650 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 660 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0
## 670 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 680 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 690 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 700 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 710 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 720 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 730 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 740 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 790 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
##
## 79 81 82 83 84 85 87 88 89 90 91 92 93 94 95 96 97 98 99
## 450 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 460 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 500 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 520 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 530 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 540 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 550 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 560 1 1 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 570 0 0 2 0 0 0 0 0 1 0 0 0 1 0 1 0 0 0 0
## 580 2 0 0 2 0 0 0 0 1 0 1 0 0 0 0 0 0 0 0
## 590 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 0 0
## 600 0 0 1 0 1 0 1 0 2 0 1 0 0 0 0 0 1 0 1
## 610 0 0 1 1 0 0 1 0 2 0 0 0 0 0 0 0 0 0 0
## 620 1 1 1 0 1 1 1 1 2 0 0 0 1 0 0 0 2 0 0
## 630 3 0 1 2 1 1 2 0 0 0 0 0 2 0 0 1 0 0 0
## 640 2 0 0 0 0 0 1 0 1 0 0 0 1 0 0 0 0 0 0
## 650 2 0 1 0 0 0 1 0 3 0 1 0 1 0 1 0 0 0 1
## 660 0 1 0 1 1 0 0 1 0 1 1 0 0 0 2 0 1 0 1
## 670 0 0 0 3 1 0 2 0 0 0 1 0 0 0 1 0 2 1 2
## 680 1 0 0 0 1 0 1 0 0 0 1 1 0 0 0 2 1 0 1
## 690 0 0 0 0 0 0 1 0 0 0 0 0 0 1 0 1 0 0 1
## 700 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 1 0
## 710 0 0 0 0 0 0 0 0 0 0 0 0 2 0 2 1 0 0 1
## 720 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0
## 730 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0
## 740 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 3
## 790 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1
##creating tables.
table(mba$gmat_vpc,mba$gmat_tpc)
##
## 0 37 44 51 52 58 61 62 65 68 69 71 72 73 75 77 78 79 80 81 83 84 85
## 16 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 22 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 30 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 33 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0
## 37 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0
## 41 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 0 0 0
## 45 0 0 0 1 0 0 0 1 1 0 1 0 1 0 0 0 0 0 0 0 1 0 0
## 46 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 50 0 0 0 0 0 0 0 0 0 1 0 1 0 0 0 0 0 0 1 0 0 0 0
## 54 0 0 0 0 1 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0
## 58 0 0 0 0 0 0 0 0 0 0 2 0 2 0 2 0 0 1 0 1 1 0 0
## 62 0 0 0 0 0 0 1 0 1 0 0 0 0 0 1 0 0 0 0 0 2 0 0
## 63 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 67 0 0 0 0 0 1 0 0 0 0 0 0 1 0 0 0 0 1 1 0 1 0 1
## 71 1 0 0 0 0 0 0 0 0 0 0 0 2 0 1 0 5 0 0 0 0 0 0
## 74 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 0 0 0 1 0 0
## 75 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 78 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 0 0 2 0
## 81 0 0 0 0 0 0 0 0 0 0 0 0 3 0 0 0 1 0 0 2 1 2 0
## 82 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0
## 84 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 1 1 0 0
## 85 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 87 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0
## 89 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0
## 90 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 91 0 0 0 0 0 0 0 0 0 0 0 0 1 0 0 0 0 0 0 0 1 0 0
## 92 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 93 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 95 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 0
## 96 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 97 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 98 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 99 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
##
## 86 87 88 89 90 91 92 93 94 95 96 97 98 99
## 16 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 22 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 30 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 33 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 37 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 41 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 45 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 46 1 0 0 0 0 0 0 0 0 0 0 0 0 0
## 50 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 54 0 1 0 0 0 0 0 0 0 0 0 0 0 0
## 58 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 62 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 63 0 0 1 0 0 0 0 1 0 0 0 0 0 0
## 67 1 0 0 0 0 0 0 0 0 0 0 0 0 0
## 71 1 1 0 1 0 1 0 0 0 1 0 0 0 0
## 74 0 5 0 0 0 0 0 0 0 0 1 0 0 0
## 75 0 0 0 0 0 1 0 0 0 0 0 0 0 0
## 78 0 0 0 0 0 1 0 0 0 0 0 0 0 0
## 81 2 1 0 0 1 1 0 1 1 2 2 0 0 0
## 82 0 0 0 0 0 0 0 0 0 0 0 0 0 0
## 84 1 1 0 2 0 1 0 3 1 0 0 0 0 0
## 85 0 0 0 1 0 0 0 0 0 0 2 0 0 0
## 87 1 0 1 4 1 0 0 1 0 0 1 2 0 0
## 89 0 1 0 1 1 0 0 1 0 1 0 1 0 0
## 90 0 0 0 0 0 0 0 0 0 1 0 1 0 0
## 91 0 0 0 2 0 0 0 2 0 0 0 0 0 0
## 92 0 0 0 0 0 0 1 0 1 0 0 0 0 1
## 93 1 0 0 1 0 1 0 1 2 1 0 1 1 0
## 95 0 0 0 2 0 1 0 1 1 2 0 1 3 0
## 96 0 1 0 0 0 0 0 0 0 1 2 0 1 0
## 97 0 0 0 0 0 0 0 0 0 0 1 0 0 1
## 98 1 1 0 0 0 0 1 0 0 1 2 0 4 5
## 99 0 0 0 0 0 0 0 0 0 1 1 0 0 2
--------------------chi-square test-------------------------
##chisquare test
chisq.test(mba$salary,mba$satis)
## Warning in chisq.test(mba$salary, mba$satis): Chi-squared approximation may
## be incorrect
##
## Pearson's Chi-squared test
##
## data: mba$salary and mba$satis
## X-squared = 391.04, df = 301, p-value = 0.0003578
##chisquare test
chisq.test(mba$s_avg,mba$f_avg)
## Warning in chisq.test(mba$s_avg, mba$f_avg): Chi-squared approximation may
## be incorrect
##
## Pearson's Chi-squared test
##
## data: mba$s_avg and mba$f_avg
## X-squared = 1033.1, df = 494, p-value < 2.2e-16
chisq.test(mba$age,mba$sex)
## Warning in chisq.test(mba$age, mba$sex): Chi-squared approximation may be
## incorrect
##
## Pearson's Chi-squared test
##
## data: mba$age and mba$sex
## X-squared = 15.118, df = 14, p-value = 0.3702
-------------------------T-test------------------------------
##t-test
attach(mba)
t.test(salary,sex)
##
## Welch Two Sample t-test
##
## data: salary and sex
## t = 15.012, df = 183, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 50475.22 65750.98
## sample estimates:
## mean of x mean of y
## 58114.342391 1.244565
-----------------------Regression model----------------------------
##regression model
reg <- lm(mba$salary~mba$gmat_tot+mba$gmat_qpc)
summary(reg)
##
## Call:
## lm(formula = mba$salary ~ mba$gmat_tot + mba$gmat_qpc)
##
## Residuals:
## Min 1Q Median 3Q Max
## -80512 -53628 26771 42639 145813
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 130669.17 44862.42 2.913 0.00403 **
## mba$gmat_tot -72.77 95.18 -0.765 0.44551
## mba$gmat_qpc -334.92 381.14 -0.879 0.38071
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 52210 on 181 degrees of freedom
## Multiple R-squared: 0.02226, Adjusted R-squared: 0.01146
## F-statistic: 2.06 on 2 and 181 DF, p-value: 0.1304
fit <- lm(salary~work_yrs+gmat_tot+s_avg+f_avg,data = mba)
summary(fit)
##
## Call:
## lm(formula = salary ~ work_yrs + gmat_tot + s_avg + f_avg, data = mba)
##
## Residuals:
## Min 1Q Median 3Q Max
## -89213 -49145 21292 43622 132708
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 44421.05 50786.86 0.875 0.38293
## work_yrs 2550.59 1568.99 1.626 0.10579
## gmat_tot -132.34 69.73 -1.898 0.05932 .
## s_avg 34331.82 11788.51 2.912 0.00404 **
## f_avg -5471.92 8866.60 -0.617 0.53793
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 50600 on 179 degrees of freedom
## Multiple R-squared: 0.09184, Adjusted R-squared: 0.07154
## F-statistic: 4.525 on 4 and 179 DF, p-value: 0.001661