store24
Aditya.S
12 February 2018
Analysis of the Case Store24 (A): Managing Employee Retention
#setup
store<-read.csv("C:\\Users\\ADI\\Downloads\\Store24.csv")TASK 4c summary statistics of the data
library(psych)
describe(store)## vars n mean sd median trimmed mad
## store 1 75 38.00 21.79 38.00 38.00 28.17
## Sales 2 75 1205413.12 304531.31 1127332.00 1182031.25 288422.04
## Profit 3 75 276313.61 89404.08 265014.00 270260.34 90532.00
## MTenure 4 75 45.30 57.67 24.12 33.58 29.67
## CTenure 5 75 13.93 17.70 7.21 10.60 6.14
## Pop 6 75 9825.59 5911.67 8896.00 9366.07 7266.22
## Comp 7 75 3.79 1.31 3.63 3.66 0.82
## Visibility 8 75 3.08 0.75 3.00 3.07 0.00
## PedCount 9 75 2.96 0.99 3.00 2.97 1.48
## Res 10 75 0.96 0.20 1.00 1.00 0.00
## Hours24 11 75 0.84 0.37 1.00 0.92 0.00
## CrewSkill 12 75 3.46 0.41 3.50 3.47 0.34
## MgrSkill 13 75 3.64 0.41 3.59 3.62 0.45
## ServQual 14 75 87.15 12.61 89.47 88.62 15.61
## min max range skew kurtosis se
## store 1.00 75.00 74.00 0.00 -1.25 2.52
## Sales 699306.00 2113089.00 1413783.00 0.71 -0.09 35164.25
## Profit 122180.00 518998.00 396818.00 0.62 -0.21 10323.49
## MTenure 0.00 277.99 277.99 2.01 3.90 6.66
## CTenure 0.89 114.15 113.26 3.52 15.00 2.04
## Pop 1046.00 26519.00 25473.00 0.62 -0.23 682.62
## Comp 1.65 11.13 9.48 2.48 11.31 0.15
## Visibility 2.00 5.00 3.00 0.25 -0.38 0.09
## PedCount 1.00 5.00 4.00 0.00 -0.52 0.11
## Res 0.00 1.00 1.00 -4.60 19.43 0.02
## Hours24 0.00 1.00 1.00 -1.82 1.32 0.04
## CrewSkill 2.06 4.64 2.58 -0.43 1.64 0.05
## MgrSkill 2.96 4.62 1.67 0.27 -0.53 0.05
## ServQual 57.90 100.00 42.10 -0.66 -0.72 1.46TASK 4d mean and standard deviation of Profit,MTenure,CTenure
"profit"## [1] "profit"mean(store$Profit)## [1] 276313.6sd(store$Profit)## [1] 89404.08"MTenure"## [1] "MTenure"mean(store$MTenure)## [1] 45.29644sd(store$MTenure)## [1] 57.67155"CTenure"## [1] "CTenure"mean(store$CTenure)## [1] 13.9315sd(store$CTenure)## [1] 17.69752TASK 4e Sorting and Subsetting data in R with mtcars
attach(mtcars)
View(mtcars)
newdata <- mtcars[order(mpg),] # sort by mpg (ascending)
View(newdata)
newdata[1:5,] # see the first 5 rows## mpg cyl disp hp drat wt qsec vs am gear carb
## Cadillac Fleetwood 10.4 8 472 205 2.93 5.250 17.98 0 0 3 4
## Lincoln Continental 10.4 8 460 215 3.00 5.424 17.82 0 0 3 4
## Camaro Z28 13.3 8 350 245 3.73 3.840 15.41 0 0 3 4
## Duster 360 14.3 8 360 245 3.21 3.570 15.84 0 0 3 4
## Chrysler Imperial 14.7 8 440 230 3.23 5.345 17.42 0 0 3 4newdata <- mtcars[order(-mpg),] # sort by mpg (descending)
View(newdata)
detach(mtcars)TASK 4f {StoreID, Sales, Profit, MTenure, CTenure} of the top 10 most profitable stores.
prder<-store[order(-store$Profit),]
prder[1:10,1:5]## store Sales Profit MTenure CTenure
## 74 74 1782957 518998 171.09720 29.519510
## 7 7 1809256 476355 62.53080 7.326488
## 9 9 2113089 474725 108.99350 6.061602
## 6 6 1703140 469050 149.93590 11.351130
## 44 44 1807740 439781 182.23640 114.151900
## 2 2 1619874 424007 86.22219 6.636550
## 45 45 1602362 410149 47.64565 9.166325
## 18 18 1704826 394039 239.96980 33.774130
## 11 11 1583446 389886 44.81977 2.036961
## 47 47 1665657 387853 12.84790 6.636550{StoreID, Sales, Profit, MTenure, CTenure} of the bottom 10 least profitable stores.
prder2<-store[order(store$Profit),]
prder2[1:10,1:5]## store Sales Profit MTenure CTenure
## 57 57 699306 122180 24.3485700 2.956879
## 66 66 879581 146058 115.2039000 3.876797
## 41 41 744211 147327 14.9180200 11.926080
## 55 55 925744 147672 6.6703910 18.365500
## 32 32 828918 149033 36.0792600 6.636550
## 13 13 857843 152513 0.6571813 1.577002
## 54 54 811190 159792 6.6703910 3.876797
## 52 52 1073008 169201 24.1185600 3.416838
## 61 61 716589 177046 21.8184200 13.305950
## 37 37 1202917 187765 23.1985000 1.347023TASK 4g scatter plot of Profit vs. MTenure.
library(car)##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logitscatterplot(Profit ~ MTenure, data=store,spread=FALSE, smoother.args=list(lty=2), main="Scatterplot of Profit vs. MTenure",xlab="MTenure",ylab="Profit")
TASK 4h scatter plot of Profit vs. CTenure.
scatterplot(Profit ~ CTenure, data=store,spread=FALSE, smoother.args=list(lty=2), main="Scatterplot of Profit vs. CTenure",xlab="CTenure",ylab="Profit")
TASK 4i Correlation Matrix for all the variables in the dataset.
round(cor(store, use="complete.obs", method="kendall"),2)## store Sales Profit MTenure CTenure Pop Comp Visibility
## store 1.00 -0.16 -0.14 -0.01 -0.01 -0.19 -0.02 -0.02
## Sales -0.16 1.00 0.78 0.26 0.14 0.20 -0.18 0.15
## Profit -0.14 0.78 1.00 0.25 0.19 0.23 -0.26 0.14
## MTenure -0.01 0.26 0.25 1.00 0.10 -0.04 0.12 0.01
## CTenure -0.01 0.14 0.19 0.10 1.00 -0.13 -0.11 0.05
## Pop -0.19 0.20 0.23 -0.04 -0.13 1.00 -0.11 0.01
## Comp -0.02 -0.18 -0.26 0.12 -0.11 -0.11 1.00 0.07
## Visibility -0.02 0.15 0.14 0.01 0.05 0.01 0.07 1.00
## PedCount -0.14 0.31 0.32 0.00 -0.05 0.46 -0.22 -0.11
## Res -0.03 -0.13 -0.15 0.04 -0.10 -0.17 0.19 0.02
## Hours24 0.02 0.07 0.02 -0.09 0.02 -0.24 0.10 0.04
## CrewSkill -0.03 0.11 0.11 0.12 0.17 0.16 -0.05 -0.18
## MgrSkill -0.06 0.18 0.15 0.19 0.02 0.03 0.17 0.01
## ServQual -0.23 0.28 0.25 0.17 0.06 0.06 0.06 0.16
## PedCount Res Hours24 CrewSkill MgrSkill ServQual
## store -0.14 -0.03 0.02 -0.03 -0.06 -0.23
## Sales 0.31 -0.13 0.07 0.11 0.18 0.28
## Profit 0.32 -0.15 0.02 0.11 0.15 0.25
## MTenure 0.00 0.04 -0.09 0.12 0.19 0.17
## CTenure -0.05 -0.10 0.02 0.17 0.02 0.06
## Pop 0.46 -0.17 -0.24 0.16 0.03 0.06
## Comp -0.22 0.19 0.10 -0.05 0.17 0.06
## Visibility -0.11 0.02 0.04 -0.18 0.01 0.16
## PedCount 1.00 -0.26 -0.29 0.12 0.05 -0.05
## Res -0.26 1.00 -0.09 -0.16 -0.03 0.09
## Hours24 -0.29 -0.09 1.00 0.14 0.00 0.04
## CrewSkill 0.12 -0.16 0.14 1.00 0.05 -0.01
## MgrSkill 0.05 -0.03 0.00 0.05 1.00 0.24
## ServQual -0.05 0.09 0.04 -0.01 0.24 1.00TASK 4j correlation between Profit and MTenure.
round(cor(store$Profit, store$MTenure),2)## [1] 0.44correlation between Profit and CTenure.
round(cor(store$Profit, store$CTenure),2)## [1] 0.26TASK 4k Corrgram based on all variables in the dataset.
library(corrgram)
corrgram(store, lower.panel=panel.shade, upper.panel=panel.pie, text.panel=panel.txt, main="Corrgram of store variables")
TASK 4l Pearson’s Correlation test on the correlation between Profit and MTenure.
cor.test(store$Profit, store$MTenure)##
## Pearson's product-moment correlation
##
## data: store$Profit and store$MTenure
## t = 4.1731, df = 73, p-value = 8.193e-05
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.2353497 0.6055175
## sample estimates:
## cor
## 0.4388692p-value= 8e-05
Pearson’s Correlation test on the correlation between Profit and CTenure
cor.test(store$Profit,store$CTenure)##
## Pearson's product-moment correlation
##
## data: store$Profit and store$CTenure
## t = 2.2786, df = 73, p-value = 0.02562
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.03262507 0.45786339
## sample estimates:
## cor
## 0.2576789p-value=0.03
TASK 3m regression of Profit on {MTenure, CTenure Comp, Pop, PedCount, Res, Hours24, Visibility}.
reg<-lm(Profit~ MTenure+ CTenure+ Comp+ Pop+ PedCount+ Res+ Hours24+Visibility, store)
summary(reg)##
## Call:
## lm(formula = Profit ~ MTenure + CTenure + Comp + Pop + PedCount +
## Res + Hours24 + Visibility, data = store)
##
## Residuals:
## Min 1Q Median 3Q Max
## -105789 -35946 -7069 33780 112390
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7610.041 66821.994 0.114 0.909674
## MTenure 760.993 127.086 5.988 9.72e-08 ***
## CTenure 944.978 421.687 2.241 0.028400 *
## Comp -25286.887 5491.937 -4.604 1.94e-05 ***
## Pop 3.667 1.466 2.501 0.014890 *
## PedCount 34087.359 9073.196 3.757 0.000366 ***
## Res 91584.675 39231.283 2.334 0.022623 *
## Hours24 63233.307 19641.114 3.219 0.001994 **
## Visibility 12625.447 9087.620 1.389 0.169411
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 56970 on 66 degrees of freedom
## Multiple R-squared: 0.6379, Adjusted R-squared: 0.594
## F-statistic: 14.53 on 8 and 66 DF, p-value: 5.382e-12TASK 4n explanatory variable(s) whose beta-coefficients are statistically significant (p < 0.05) - MTenure, CTenure Comp, Pop, PedCount, Res, Hours24
explanatory variable(s) whose beta-coefficients are not statistically significant (p > 0.05) - Visibility
TASK 4o expected change in the Profit at a store, if the Manager’s tenure i.e. number of months of experience with Store24, increases by one month
reg$coefficients[2]## MTenure
## 760.9927expected change in the Profit at a store, if the Crew’s tenure i.e. number of months of experience with Store24, increases by one month
reg$coefficients[3]## CTenure
## 944.978TASK 4p Executive summary:- It is observed that profit of a store is dependent on tenure of both managers and crew. correlation between profits and manager tenure is higher than with crew tenure. Expected profits is however higher with increase in crew tenure when compared to manager tenure.Multiple R-squared: 0.638 implies that the model accounts for 63.8% of the variance in weights. p-value: 5.38e-12 <0.01 indicates that it is a good regression model.