Dean’s Dilemma
Ambalika
December 10, 2017
ddilemma.df <- read.csv(paste("Data - Deans Dilemma.csv", sep=""))Summary Statistics of the data
attach(ddilemma.df) # attaching the columns of the data frame
library(psych)
describe(ddilemma.df) # using describe function## vars n mean sd median trimmed
## SlNo 1 391 196.00 113.02 196.00 196.00
## Gender* 2 391 1.68 0.47 2.00 1.72
## Gender.B 3 391 0.32 0.47 0.00 0.28
## Percent_SSC 4 391 64.65 10.96 64.50 64.76
## Board_SSC* 5 391 2.23 0.87 3.00 2.28
## Board_CBSE 6 391 0.29 0.45 0.00 0.24
## Board_ICSE 7 391 0.20 0.40 0.00 0.12
## Percent_HSC 8 391 63.80 11.42 63.00 63.34
## Board_HSC* 9 391 2.39 0.85 3.00 2.48
## Stream_HSC* 10 391 2.34 0.56 2.00 2.36
## Percent_Degree 11 391 62.98 8.92 63.00 62.91
## Course_Degree* 12 391 3.85 1.61 4.00 3.81
## Degree_Engg 13 391 0.09 0.29 0.00 0.00
## Experience_Yrs 14 391 0.48 0.67 0.00 0.36
## Entrance_Test* 15 391 5.85 1.35 6.00 6.08
## S.TEST 16 391 0.83 0.38 1.00 0.91
## Percentile_ET 17 391 54.93 31.17 62.00 56.87
## S.TEST.SCORE 18 391 54.93 31.17 62.00 56.87
## Percent_MBA 19 391 61.67 5.85 61.01 61.45
## Specialization_MBA* 20 391 1.47 0.56 1.00 1.42
## Marks_Communication 21 391 60.54 8.82 58.00 59.68
## Marks_Projectwork 22 391 68.36 7.15 69.00 68.60
## Marks_BOCA 23 391 64.38 9.58 63.00 64.08
## Placement* 24 391 1.80 0.40 2.00 1.87
## Placement_B 25 391 0.80 0.40 1.00 0.87
## Salary 26 391 219078.26 138311.65 240000.00 217011.50
## mad min max range skew kurtosis
## SlNo 145.29 1.00 391.00 390.00 0.00 -1.21
## Gender* 0.00 1.00 2.00 1.00 -0.75 -1.45
## Gender.B 0.00 0.00 1.00 1.00 0.75 -1.45
## Percent_SSC 12.60 37.00 87.20 50.20 -0.06 -0.72
## Board_SSC* 0.00 1.00 3.00 2.00 -0.45 -1.53
## Board_CBSE 0.00 0.00 1.00 1.00 0.93 -1.14
## Board_ICSE 0.00 0.00 1.00 1.00 1.52 0.31
## Percent_HSC 13.34 40.00 94.70 54.70 0.29 -0.67
## Board_HSC* 0.00 1.00 3.00 2.00 -0.83 -1.13
## Stream_HSC* 0.00 1.00 3.00 2.00 -0.12 -0.72
## Percent_Degree 8.90 35.00 89.00 54.00 0.05 0.24
## Course_Degree* 1.48 1.00 7.00 6.00 0.00 -1.08
## Degree_Engg 0.00 0.00 1.00 1.00 2.76 5.63
## Experience_Yrs 0.00 0.00 3.00 3.00 1.27 1.17
## Entrance_Test* 0.00 1.00 9.00 8.00 -2.52 7.04
## S.TEST 0.00 0.00 1.00 1.00 -1.74 1.02
## Percentile_ET 25.20 0.00 98.69 98.69 -0.74 -0.69
## S.TEST.SCORE 25.20 0.00 98.69 98.69 -0.74 -0.69
## Percent_MBA 6.39 50.83 77.89 27.06 0.34 -0.52
## Specialization_MBA* 0.00 1.00 3.00 2.00 0.70 -0.56
## Marks_Communication 8.90 50.00 88.00 38.00 0.74 -0.25
## Marks_Projectwork 7.41 50.00 87.00 37.00 -0.26 -0.27
## Marks_BOCA 11.86 50.00 96.00 46.00 0.29 -0.85
## Placement* 0.00 1.00 2.00 1.00 -1.48 0.19
## Placement_B 0.00 0.00 1.00 1.00 -1.48 0.19
## Salary 88956.00 0.00 940000.00 940000.00 0.24 1.74
## se
## SlNo 5.72
## Gender* 0.02
## Gender.B 0.02
## Percent_SSC 0.55
## Board_SSC* 0.04
## Board_CBSE 0.02
## Board_ICSE 0.02
## Percent_HSC 0.58
## Board_HSC* 0.04
## Stream_HSC* 0.03
## Percent_Degree 0.45
## Course_Degree* 0.08
## Degree_Engg 0.01
## Experience_Yrs 0.03
## Entrance_Test* 0.07
## S.TEST 0.02
## Percentile_ET 1.58
## S.TEST.SCORE 1.58
## Percent_MBA 0.30
## Specialization_MBA* 0.03
## Marks_Communication 0.45
## Marks_Projectwork 0.36
## Marks_BOCA 0.48
## Placement* 0.02
## Placement_B 0.02
## Salary 6994.72Dimension of the data frame
dim(ddilemma.df)## [1] 391 26median(ddilemma.df$Salary)## [1] 240000Median Salary of all students in the data sample= 240000
prop.table(table(ddilemma.df$Placement))##
## Not Placed Placed
## 0.202046 0.797954Percentage of students who were placed= 79.80%
STUDENTS WHO WERE SUCCESSFULLY PLACED:
placed.df <- ddilemma.df[ which(ddilemma.df$Placement=='Placed'), ] median(placed.df$Salary)## [1] 260000Median salary of students who were placed = 260000
Mean salary of males and females, who were placed
aggregate(Salary ~ Gender, data = placed.df, mean)## Gender Salary
## 1 F 253068.0
## 2 M 284241.9MBA performance of the students who were placed
hist(placed.df$Percent_MBA, main = " MBA performance of the students who were placed ", xlab = "MBA Percentage", ylab = "Count", breaks = 3, col = "red")
STUDENTS WHO WERE NOT PLACED:
notplaced.df <- ddilemma.df[ which(ddilemma.df$Placement == 'Not Placed'), ]Representing students who were placed after the MBA and who also gave some MBA entrance test before admission into the MBA progra:-
placedET.df <- placed.df[ which(placed.df$S.TEST == "1"), ]