RawdataSummary <- describe(DeansDilemmaRaw)
RawdataSummary
## 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 6994.72
MedianSalary <- median(DeansDilemmaRaw$Salary)
MedianSalary
## [1] 240000
Placedpercentage <- round(prop.table(table(DeansDilemmaRaw$Placement))*100, digits = 2)
Placedpercentage
##
## Not Placed Placed
## 20.2 79.8
placedstudents_df <- filter(DeansDilemmaRaw, DeansDilemmaRaw$Placement_B == "1" )
## Warning: package 'bindrcpp' was built under R version 3.4.1
##placedstudents_df
placedstudents_medianSalary <- median(placedstudents_df$Salary)
placedstudents_medianSalary
## [1] 260000
placedstudents_meanSalary_gender <- aggregate(placedstudents_df$Salary, by= list(placedstudents_df$Gender), mean)
placedstudents_meanSalary_gender
## Group.1 x
## 1 F 253068.0
## 2 M 284241.9
histogramPlaced <- hist(placedstudents_df$Percent_MBA, main = "MBA performance of placed students", xlab = "Percentage", ylab = "count", col = "grey", border = "black", breaks=c(50, 60, 70, 80))
notplaced <- filter(DeansDilemmaRaw, DeansDilemmaRaw$Placement_B == "0" )
##notplaced
par(mfrow=c(1,2))
histogramPlaced <- hist(placedstudents_df$Percent_MBA, main = "MBA performance of placed students", xlab = "Percentage", ylab = "count", col = "grey", border = "black", breaks=c(50, 60, 70, 80))
histogramNotPlaced <- hist(notplaced$Percent_MBA, main = "MBA performance of not placed students", ylab = "count", xlab = "Percentage", col = "grey", border = "black", breaks=c(50, 60, 70, 80))
malesalaryplaced <- filter(placedstudents_df, placedstudents_df$Gender == "M")
femalesalaryplaced <- filter(placedstudents_df, placedstudents_df$Gender == "F")
boxplot(femalesalaryplaced$Salary, malesalaryplaced$Salary, horizontal=TRUE, xlab="Salary", ylab = "Gender", main = "Comparison of Salary of Males and Females",names=c("Females","Males"))
placedET <- filter(DeansDilemmaRaw, DeansDilemmaRaw$Placement_B == "1" & DeansDilemmaRaw$Entrance_Test != "None")
##placedET
library(car)
##
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
##
## recode
## The following object is masked from 'package:psych':
##
## logit
##scatterplotmatrix <- pairs(~Salary + Percent_MBA + Percentile_ET, data = placedET, main = "Scatter Plot Matrix")
##scatterplotmatrix
scatterplotmatrix <- scatterplot.matrix(~Salary + Percent_MBA + Percentile_ET, data = placedET, main = "Scatter Plot Matrix", spread = FALSE)
## Warning: 'scatterplot.matrix' is deprecated.
## Use 'scatterplotMatrix' instead.
## See help("Deprecated") and help("car-deprecated").
scatterplotmatrix
## NULL