# Task 4a:
# --> The management wants to make make more informed decisions when considering increasing wages and bonuses or how much to spend on training and development programs.
# --> They also want to use their data to help understand how important manager and crew tenure are relative to site-location factors such as population, number of competitors, and pedestrian access in determining store level financial performance and understand how important manager and crew tenure are relative to people factors such as employee skill and experiences in optimizing a given site's performance.
# Task 4b:
# The dataset has the following variables that can help establish relationships between them to answer the above questions.They can find the relationship between sales, profit and Mtenure and Ctenure to establish whether increase in tenure has a positive impact on sales and profit. Also, they can find the relationship between pop, Comp, Visible,PedCount, Hours24,Res and Mtenure and Ctenure to establish whether increase in tenure has a positive impact on sales and profit. Moreover, they can find the relationship between MgrSkill, crewSkill and Mtenure and Ctenure to establish whether employee skill and experiences has a positive impact on sales and profit.
# Task 4c:
setwd("C:/Users/Dixit/iim_internship/Week_3/Day_1")
store <- read.csv(file="Store24.csv",head=TRUE,sep=",")
View(store)
library(psych)
summaryOfStore <- describe(store)
StoreSum <- summaryOfStore[ c(3,4,5,8,9)]
StoreSum
## mean sd median min max
## store 38.00 21.79 38.00 1.00 75.00
## Sales 1205413.12 304531.31 1127332.00 699306.00 2113089.00
## Profit 276313.61 89404.08 265014.00 122180.00 518998.00
## MTenure 45.30 57.67 24.12 0.00 277.99
## CTenure 13.93 17.70 7.21 0.89 114.15
## Pop 9825.59 5911.67 8896.00 1046.00 26519.00
## Comp 3.79 1.31 3.63 1.65 11.13
## Visibility 3.08 0.75 3.00 2.00 5.00
## PedCount 2.96 0.99 3.00 1.00 5.00
## Res 0.96 0.20 1.00 0.00 1.00
## Hours24 0.84 0.37 1.00 0.00 1.00
## CrewSkill 3.46 0.41 3.50 2.06 4.64
## MgrSkill 3.64 0.41 3.59 2.96 4.62
## ServQual 87.15 12.61 89.47 57.90 100.00
# Task 4d:
StoreSum[3:5,]
## mean sd median min max
## Profit 276313.61 89404.08 265014.00 122180.00 518998.00
## MTenure 45.30 57.67 24.12 0.00 277.99
## CTenure 13.93 17.70 7.21 0.89 114.15
# Task 4f:
ProfitStoreDesc <- store[order(-store$Profit),]
View(ProfitStoreDesc)
ProfitStoreDesc[1:10,1:5]
## store Sales Profit MTenure CTenure
## 74 74 1782957 518998 171.09720 29.519510
## 7 7 1809256 476355 62.53080 7.326488
## 9 9 2113089 474725 108.99350 6.061602
## 6 6 1703140 469050 149.93590 11.351130
## 44 44 1807740 439781 182.23640 114.151900
## 2 2 1619874 424007 86.22219 6.636550
## 45 45 1602362 410149 47.64565 9.166325
## 18 18 1704826 394039 239.96980 33.774130
## 11 11 1583446 389886 44.81977 2.036961
## 47 47 1665657 387853 12.84790 6.636550
ProfitStoreAsc <- store[order(store$Profit),]
View(ProfitStoreAsc)
ProfitStoreAsc[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 1.347023
# Task 4g:
library(car)
##
## Attaching package: 'car'
## The following object is masked from 'package:psych':
##
## logit
scatterplot(Profit~MTenure, data = store, main="Scatterplot of Profit vs Mtenure",xlab="Mtenure",
ylab="Profit", smoother=loessLine)
# Task 4h:
scatterplot(Profit~CTenure, data = store, main="Scatterplot of Profit vs Ctenure",xlab="Ctenure",
ylab="Profit", smoother=loessLine)
# Task 4i:
round(cor(store), digits=2)
## store Sales Profit MTenure CTenure Pop Comp Visibility
## store 1.00 -0.23 -0.20 -0.06 0.02 -0.29 0.03 -0.03
## Sales -0.23 1.00 0.92 0.45 0.25 0.40 -0.24 0.13
## Profit -0.20 0.92 1.00 0.44 0.26 0.43 -0.33 0.14
## MTenure -0.06 0.45 0.44 1.00 0.24 -0.06 0.18 0.16
## CTenure 0.02 0.25 0.26 0.24 1.00 0.00 -0.07 0.07
## Pop -0.29 0.40 0.43 -0.06 0.00 1.00 -0.27 -0.05
## Comp 0.03 -0.24 -0.33 0.18 -0.07 -0.27 1.00 0.03
## Visibility -0.03 0.13 0.14 0.16 0.07 -0.05 0.03 1.00
## PedCount -0.22 0.42 0.45 0.06 -0.08 0.61 -0.15 -0.14
## Res -0.03 -0.17 -0.16 -0.06 -0.34 -0.24 0.22 0.02
## Hours24 0.03 0.06 -0.03 -0.17 0.07 -0.22 0.13 0.05
## CrewSkill 0.05 0.16 0.16 0.10 0.26 0.28 -0.04 -0.20
## MgrSkill -0.07 0.31 0.32 0.23 0.12 0.08 0.22 0.07
## ServQual -0.32 0.39 0.36 0.18 0.08 0.12 0.02 0.21
## PedCount Res Hours24 CrewSkill MgrSkill ServQual
## store -0.22 -0.03 0.03 0.05 -0.07 -0.32
## Sales 0.42 -0.17 0.06 0.16 0.31 0.39
## Profit 0.45 -0.16 -0.03 0.16 0.32 0.36
## MTenure 0.06 -0.06 -0.17 0.10 0.23 0.18
## CTenure -0.08 -0.34 0.07 0.26 0.12 0.08
## Pop 0.61 -0.24 -0.22 0.28 0.08 0.12
## Comp -0.15 0.22 0.13 -0.04 0.22 0.02
## Visibility -0.14 0.02 0.05 -0.20 0.07 0.21
## PedCount 1.00 -0.28 -0.28 0.21 0.09 -0.01
## Res -0.28 1.00 -0.09 -0.15 -0.03 0.09
## Hours24 -0.28 -0.09 1.00 0.11 -0.04 0.06
## CrewSkill 0.21 -0.15 0.11 1.00 -0.02 -0.03
## MgrSkill 0.09 -0.03 -0.04 -0.02 1.00 0.36
## ServQual -0.01 0.09 0.06 -0.03 0.36 1.00
# Task 4j
round(cor(store$Profit,store$MTenure), digits=2)
## [1] 0.44
round(cor(store$Profit,store$CTenure), digits=2)
## [1] 0.26
# Task 4k
library("corrgram")
## Warning: replacing previous import by 'magrittr::%>%' when loading
## 'dendextend'
corrgram(store, order=FALSE, lower.panel=panel.shade,
upper.panel=panel.pie, text.panel=panel.txt,
main="Corrgram of store variables")
# Task 4l
cor.test(store$Profit, store$MTenure, method="pearson")
##
## 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
## 0.4388692
cor.test(store$Profit, store$CTenure, method="pearson")
##
## 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
## 0.2576789
# Task 4m
ProfitlmMod <- lm(formula = Profit ~ MTenure + CTenure + Comp + Pop + PedCount +
Res + Hours24 + CrewSkill, data = store)
summary(ProfitlmMod)
##
## Call:
## lm(formula = Profit ~ MTenure + CTenure + Comp + Pop + PedCount +
## Res + Hours24 + CrewSkill, data = store)
##
## Residuals:
## Min 1Q Median 3Q Max
## -115203 -29815 -7920 24073 115787
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 121335.197 77044.205 1.575 0.120066
## MTenure 806.634 125.321 6.437 1.61e-08 ***
## CTenure 1107.371 433.793 2.553 0.013008 *
## Comp -25294.903 5477.740 -4.618 1.85e-05 ***
## Pop 4.294 1.495 2.872 0.005483 **
## PedCount 33882.432 9018.906 3.757 0.000367 ***
## Res 95189.799 39187.386 2.429 0.017867 *
## Hours24 70461.295 19978.468 3.527 0.000770 ***
## CrewSkill -27259.352 18060.985 -1.509 0.135996
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 56820 on 66 degrees of freedom
## Multiple R-squared: 0.6398, Adjusted R-squared: 0.5961
## F-statistic: 14.65 on 8 and 66 DF, p-value: 4.585e-12
# Task 4n
#Mtenure, Comp, Pop, PedCount, Hours24 are the explanatory variable(s) whose beta-coefficients are statistically significant (p < 0.05).Ctenure, Res, CrewSkill are the explanatory variable(s) whose beta-coefficients are not statistically significant (p > 0.05).
# Task 4o:
# If the Mtenure increases by 1 month. as Mtenure is positively correlated, the profit will increase by 806.634. If the Ctenure increases by 1 month. as Ctenure is positively correlated, the profit will increase by 1107.371.
# Task 4p
#The regression model shows that competitors is a negatively correlated variable, which should be tried to be kept low by the decision makers inorder to increase profits. The linear model built also shows that explanatory variable(s) whose beta-coefficients are statistically significant (p < 0.05) are Mtenure, Comp, Pop, PedCount, Hours24.Seeing ProfitStoreDesc and ProfitStoreAsc, we can see profits and sales are higher if the positively correlated variables(Like MTenure, CTenure, Visible etc) are high and the negative one like the competitors are low. Also, seeing the scatterplot between Profit and Mtenure, it definitely shows positive coorelation, saying that by increasing their tenure, profits surely will increase, suggesting the decision makers to work on these parameters.