R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

store<- read.csv(paste("Store24.csv", sep=""))
summary(store)
##      store          Sales             Profit          MTenure      
##  Min.   : 1.0   Min.   : 699306   Min.   :122180   Min.   :  0.00  
##  1st Qu.:19.5   1st Qu.: 984579   1st Qu.:211004   1st Qu.:  6.67  
##  Median :38.0   Median :1127332   Median :265014   Median : 24.12  
##  Mean   :38.0   Mean   :1205413   Mean   :276314   Mean   : 45.30  
##  3rd Qu.:56.5   3rd Qu.:1362388   3rd Qu.:331314   3rd Qu.: 50.92  
##  Max.   :75.0   Max.   :2113089   Max.   :518998   Max.   :277.99  
##     CTenure              Pop             Comp          Visibility  
##  Min.   :  0.8871   Min.   : 1046   Min.   : 1.651   Min.   :2.00  
##  1st Qu.:  4.3943   1st Qu.: 5616   1st Qu.: 3.151   1st Qu.:3.00  
##  Median :  7.2115   Median : 8896   Median : 3.629   Median :3.00  
##  Mean   : 13.9315   Mean   : 9826   Mean   : 3.788   Mean   :3.08  
##  3rd Qu.: 17.2156   3rd Qu.:14104   3rd Qu.: 4.230   3rd Qu.:4.00  
##  Max.   :114.1519   Max.   :26519   Max.   :11.128   Max.   :5.00  
##     PedCount         Res          Hours24       CrewSkill    
##  Min.   :1.00   Min.   :0.00   Min.   :0.00   Min.   :2.060  
##  1st Qu.:2.00   1st Qu.:1.00   1st Qu.:1.00   1st Qu.:3.225  
##  Median :3.00   Median :1.00   Median :1.00   Median :3.500  
##  Mean   :2.96   Mean   :0.96   Mean   :0.84   Mean   :3.457  
##  3rd Qu.:4.00   3rd Qu.:1.00   3rd Qu.:1.00   3rd Qu.:3.655  
##  Max.   :5.00   Max.   :1.00   Max.   :1.00   Max.   :4.640  
##     MgrSkill        ServQual     
##  Min.   :2.957   Min.   : 57.90  
##  1st Qu.:3.344   1st Qu.: 78.95  
##  Median :3.589   Median : 89.47  
##  Mean   :3.638   Mean   : 87.15  
##  3rd Qu.:3.925   3rd Qu.: 99.90  
##  Max.   :4.622   Max.   :100.00
library(psych)
describe(store$Profit)
##    vars  n     mean       sd median  trimmed   mad    min    max  range
## X1    1 75 276313.6 89404.08 265014 270260.3 90532 122180 518998 396818
##    skew kurtosis       se
## X1 0.62    -0.21 10323.49
describe(store$MTenure)
##    vars  n mean    sd median trimmed   mad min    max  range skew kurtosis
## X1    1 75 45.3 57.67  24.12   33.58 29.67   0 277.99 277.99 2.01      3.9
##      se
## X1 6.66
describe(store$CTenure)
##    vars  n  mean   sd median trimmed  mad  min    max  range skew kurtosis
## X1    1 75 13.93 17.7   7.21    10.6 6.14 0.89 114.15 113.26 3.52       15
##      se
## X1 2.04
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
store1 <- select(store, store, Sales, Profit, MTenure, CTenure)
newdata <- store1[order(store1$Profit), ]
names(newdata)[1] <- "StoreID"
newdata[1:10, ]
##    StoreID   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
newdata[66:75, ]
##    StoreID   Sales Profit   MTenure    CTenure
## 47      47 1665657 387853  12.84790   6.636550
## 11      11 1583446 389886  44.81977   2.036961
## 18      18 1704826 394039 239.96980  33.774130
## 45      45 1602362 410149  47.64565   9.166325
## 2        2 1619874 424007  86.22219   6.636550
## 44      44 1807740 439781 182.23640 114.151900
## 6        6 1703140 469050 149.93590  11.351130
## 9        9 2113089 474725 108.99350   6.061602
## 7        7 1809256 476355  62.53080   7.326488
## 74      74 1782957 518998 171.09720  29.519510
library(car)
## 
## Attaching package: 'car'
## The following object is masked from 'package:dplyr':
## 
##     recode
## The following object is masked from 'package:psych':
## 
##     logit
scatterplot(store$Profit ~ store$MTenure, main = "Scatterplot of Profit vs. MTenure", xlab = "MTenure", ylab = "Profit")

scatterplot(store$Profit ~ store$CTenure, main = "Scatterplot of Profit vs. CTenure", xlab = "CTenure", ylab = "Profit")

cor(store)
##                  store       Sales      Profit     MTenure      CTenure
## store       1.00000000 -0.22693400 -0.19993481 -0.05655216  0.019930097
## Sales      -0.22693400  1.00000000  0.92387059  0.45488023  0.254315184
## Profit     -0.19993481  0.92387059  1.00000000  0.43886921  0.257678895
## MTenure    -0.05655216  0.45488023  0.43886921  1.00000000  0.243383135
## CTenure     0.01993010  0.25431518  0.25767890  0.24338314  1.000000000
## Pop        -0.28936691  0.40348147  0.43063326 -0.06089646 -0.001532449
## Comp        0.03194023 -0.23501372 -0.33454148  0.18087179 -0.070281327
## Visibility -0.02648858  0.13065638  0.13569207  0.15651731  0.066506016
## PedCount   -0.22117519  0.42391087  0.45023346  0.06198608 -0.084112627
## Res        -0.03142976 -0.16672402 -0.15947734 -0.06234721 -0.340340876
## Hours24     0.02687986  0.06324716 -0.02568703 -0.16513872  0.072865022
## CrewSkill   0.04866273  0.16402179  0.16008443  0.10162169  0.257154817
## MgrSkill   -0.07218804  0.31163056  0.32284842  0.22962743  0.124045346
## ServQual   -0.32246921  0.38638112  0.36245032  0.18168875  0.081156172
##                     Pop        Comp  Visibility     PedCount         Res
## store      -0.289366908  0.03194023 -0.02648858 -0.221175193 -0.03142976
## Sales       0.403481471 -0.23501372  0.13065638  0.423910867 -0.16672402
## Profit      0.430633264 -0.33454148  0.13569207  0.450233461 -0.15947734
## MTenure    -0.060896460  0.18087179  0.15651731  0.061986084 -0.06234721
## CTenure    -0.001532449 -0.07028133  0.06650602 -0.084112627 -0.34034088
## Pop         1.000000000 -0.26828355 -0.04998269  0.607638861 -0.23693726
## Comp       -0.268283553  1.00000000  0.02844548 -0.146325204  0.21923878
## Visibility -0.049982694  0.02844548  1.00000000 -0.141068116  0.02194756
## PedCount    0.607638861 -0.14632520 -0.14106812  1.000000000 -0.28437852
## Res        -0.236937265  0.21923878  0.02194756 -0.284378520  1.00000000
## Hours24    -0.221767927  0.12957478  0.04692587 -0.275973353 -0.08908708
## CrewSkill   0.282845090 -0.04229731 -0.19745297  0.213672596 -0.15331247
## MgrSkill    0.083554590  0.22407913  0.07348301  0.087475440 -0.03213640
## ServQual    0.123946521  0.01814508  0.20992919 -0.005445552  0.09081624
##                Hours24   CrewSkill    MgrSkill     ServQual
## store       0.02687986  0.04866273 -0.07218804 -0.322469213
## Sales       0.06324716  0.16402179  0.31163056  0.386381121
## Profit     -0.02568703  0.16008443  0.32284842  0.362450323
## MTenure    -0.16513872  0.10162169  0.22962743  0.181688755
## CTenure     0.07286502  0.25715482  0.12404535  0.081156172
## Pop        -0.22176793  0.28284509  0.08355459  0.123946521
## Comp        0.12957478 -0.04229731  0.22407913  0.018145080
## Visibility  0.04692587 -0.19745297  0.07348301  0.209929194
## PedCount   -0.27597335  0.21367260  0.08747544 -0.005445552
## Res        -0.08908708 -0.15331247 -0.03213640  0.090816237
## Hours24     1.00000000  0.10536295 -0.03883007  0.058325655
## CrewSkill   0.10536295  1.00000000 -0.02100949 -0.033516504
## MgrSkill   -0.03883007 -0.02100949  1.00000000  0.356702708
## ServQual    0.05832565 -0.03351650  0.35670271  1.000000000
cor(store$Profit, store$MTenure)
## [1] 0.4388692
cor(store$Profit, store$CTenure)
## [1] 0.2576789
library(corrgram)
corrgram(store, order = TRUE, lower.panel = panel.shade, upper.panel = panel.pie, text.panel = panel.txt, main = "Corrgram of Store variables")

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 
## 0.4388692
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 
## 0.2576789
fit <- lm(Profit ~ MTenure + CTenure + Comp + Pop + PedCount + Res + Hours24 + Visibility, data = store)
summary(fit)
## 
## 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-12

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.