library(mapproj) # map
## Warning: package 'mapproj' was built under R version 3.4.2
## Loading required package: maps
## Warning: package 'maps' was built under R version 3.4.2
library(reshape2) # melt
library(nparcomp) # gao_cs
## Warning: package 'nparcomp' was built under R version 3.4.2
## Loading required package: multcomp
## Warning: package 'multcomp' was built under R version 3.4.2
## Loading required package: mvtnorm
## Loading required package: survival
## Loading required package: TH.data
## Warning: package 'TH.data' was built under R version 3.4.2
## Loading required package: MASS
##
## Attaching package: 'TH.data'
## The following object is masked from 'package:MASS':
##
## geyser
library(car) # leveneTest and Anova Type III
## Warning: package 'car' was built under R version 3.4.2
library(heplots) # etasquared
## Warning: package 'heplots' was built under R version 3.4.2
library(MASS) # lda
library(psy) # cronbach
library(igraph) # network graphs
## Warning: package 'igraph' was built under R version 3.4.2
##
## Attaching package: 'igraph'
## The following objects are masked from 'package:stats':
##
## decompose, spectrum
## The following object is masked from 'package:base':
##
## union
library(lsr) # partial eta squared
library(psych) # KMO
##
## Attaching package: 'psych'
## The following object is masked from 'package:psy':
##
## wkappa
## The following object is masked from 'package:car':
##
## logit
library(biotools) # M Box test
## Warning: package 'biotools' was built under R version 3.4.2
## Loading required package: rpanel
## Warning: package 'rpanel' was built under R version 3.4.2
## Loading required package: tcltk
## Package `rpanel', version 1.1-3: type help(rpanel) for summary information
## Loading required package: tkrplot
## Loading required package: lattice
## Loading required package: SpatialEpi
## Warning: package 'SpatialEpi' was built under R version 3.4.2
## Loading required package: sp
## Warning: package 'sp' was built under R version 3.4.2
##
## Attaching package: 'SpatialEpi'
## The following object is masked from 'package:igraph':
##
## normalize
## ---
## biotools version 3.1
##
##
## Attaching package: 'biotools'
## The following object is masked from 'package:heplots':
##
## boxM
library(vcd) # goodfit
## Warning: package 'vcd' was built under R version 3.4.2
## Loading required package: grid
library(agricolae)
## Warning: package 'agricolae' was built under R version 3.4.2
##
## Attaching package: 'agricolae'
## The following object is masked from 'package:igraph':
##
## similarity
library(lavaan) # SEM4
## Warning: package 'lavaan' was built under R version 3.4.2
## This is lavaan 0.5-23.1097
## lavaan is BETA software! Please report any bugs.
##
## Attaching package: 'lavaan'
## The following object is masked from 'package:psych':
##
## cor2cov
library(semPlot) # SEM graph
## Warning: package 'semPlot' was built under R version 3.4.2
library(Hmisc) # correlation matrix
## Warning: package 'Hmisc' was built under R version 3.4.2
## Loading required package: Formula
## Loading required package: ggplot2
##
## Attaching package: 'ggplot2'
## The following objects are masked from 'package:psych':
##
## %+%, alpha
##
## Attaching package: 'Hmisc'
## The following object is masked from 'package:psych':
##
## describe
## The following objects are masked from 'package:base':
##
## format.pval, round.POSIXt, trunc.POSIXt, units
library(MVN) # multivariate normality
## Warning: package 'MVN' was built under R version 3.4.2
## sROC 0.1-2 loaded
##
## Attaching package: 'MVN'
## The following object is masked from 'package:psych':
##
## mardia
library(plyr) # count
##
## Attaching package: 'plyr'
## The following objects are masked from 'package:Hmisc':
##
## is.discrete, summarize
## The following object is masked from 'package:maps':
##
## ozone
## PRETEST 1
cat("\014") # cleans screen
rm(list=ls(all=TRUE)) # remove variables in working memory
setwd("C:/Users/Erik Ernesto Vazquez/Downloads/Results") # sets working directory
Pretest<-read.csv("Main_Study/Main_study__3x3_United_States.csv", skip=2, header=F) # reads raw data from Qualtrics
NamesandHeaders<-read.csv("Main_Study/Main_study__3x3_United_States.csv") # assigns headers and names to data frame
names(Pretest)<-names(NamesandHeaders)
Pretest$V6<-as.character(Pretest$V6)
Pretest<-Pretest[which(!duplicated(Pretest$V6)&Pretest$t2.frmwrk_3>0&Pretest$t12_3>0),] # This procedure displays a freq. table and a bar plot showing grouping' without IPs duplicates
framework.wide=data.frame(Pretest[1],Pretest[34:36],Pretest[596:598],Pretest[603:604])
names(framework.wide)<-c("Subject","Credence","Experience","Search","Age","Gender","Income","Education","RE")
table(framework.wide$Gender)
##
## 1 2
## 539 506
women<-subset(framework.wide,framework.wide$Gender==1)
men<-subset(framework.wide,framework.wide$Gender==2)
Pretest<-rbind(women[1:60,],men[1:60,])
table(Pretest$Gender)
##
## 1 2
## 60 60
mean(Pretest$Age)-2014
## [1] -31.25
sd(Pretest$Age)
## [1] 8.758429
aggregate(Pretest$Age,list(Pretest$Gender),mean)
## Group.1 x
## 1 1 1983.067
## 2 2 1982.433
aggregate(Pretest$Age,list(Pretest$Gender),sd)
## Group.1 x
## 1 1 8.938332
## 2 2 8.638437
women<-subset(Pretest,Pretest$Gender==1)
men<-subset(Pretest,Pretest$Gender==2)
t.test(women$Age,men$Age) ## groups are equivalent in Age
##
## Welch Two Sample t-test
##
## data: women$Age and men$Age
## t = 0.39466, df = 117.86, p-value = 0.6938
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -2.544578 3.811245
## sample estimates:
## mean of x mean of y
## 1983.067 1982.433
summary(Pretest[,2:4])
## Credence Experience Search
## Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.750 1st Qu.:3.000 1st Qu.:3.000
## Median :7.000 Median :4.000 Median :3.000
## Mean :6.125 Mean :4.675 Mean :4.117
## 3rd Qu.:8.000 3rd Qu.:6.000 3rd Qu.:6.000
## Max. :9.000 Max. :9.000 Max. :9.000
t.test(Pretest$Credence,Pretest$Experience) ## Validation of SEC levels of ease to evaluate quality
##
## Welch Two Sample t-test
##
## data: Pretest$Credence and Pretest$Experience
## t = 5.0975, df = 237.96, p-value = 7.019e-07
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.8896311 2.0103689
## sample estimates:
## mean of x mean of y
## 6.125 4.675
t.test(Pretest$Experience,Pretest$Search) ## The chance of error type 2 is very small according to Winter 2013
##
## Welch Two Sample t-test
##
## data: Pretest$Experience and Pretest$Search
## t = 2.0762, df = 235.43, p-value = 0.03896
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.02853859 1.08812808
## sample estimates:
## mean of x mean of y
## 4.675000 4.116667
framework.long<-melt(Pretest,id.vars=c("Subject","Age","Gender","Income","Education","RE"),measure.vars=c("Credence", "Experience", "Search" ),variable.name="Framework", value.name="Measurement")
aggregate(framework.long$Measurement,list(framework.long$Framework),sd)
## Group.1 x
## 1 Credence 2.217435
## 2 Experience 2.189212
## 3 Search 1.971150
## PRETEST 2
cat("\014") # cleans screen
rm(list=ls(all=TRUE)) # remove variables in working memory
setwd("C:/Users/Erik Ernesto Vazquez/Downloads/IJEC Data recollection") # sets working directory
MainStudy<-read.csv("Pretest Analysis Tie Strength and Media Richness.csv", header=T) # reads raw data from Qualtrics
MainStudy<-subset(MainStudy,MainStudy$X3<1991&MainStudy$X1_15>0&MainStudy$X2_15>0&MainStudy$X3_15>0&MainStudy$X4_15>0&MainStudy$X5_15>0)
table(MainStudy$V3)
##
## 9 10
## 25 26
MainStudyF<-subset(MainStudy,MainStudy$V3==9)
MainStudyM<-subset(MainStudy,MainStudy$V3==10)
MainStudy<-rbind(MainStudyF[1:25,],MainStudyM[1:25,])
table(MainStudy$V3)
##
## 9 10
## 25 25
mean(MainStudy$X3)-2014
## [1] -31.88
sd(MainStudy$X3)
## [1] 8.66294
##Reliability content Vividness
MainStudyMelt1<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","X1_1","X1_2","X1_3",
"X1_4","X1_5","X1_6","X1_7",
"X1_15"),
measure.vars=c("X1_1","X1_2","X1_3",
"X1_4","X1_5","X1_6","X1_7",
"X1_15"),
variable.name="MediaRichness1", value.name="MRItem1")
MainStudyMelt2<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","X2_1","X2_2","X2_3",
"X2_4","X2_5","X2_6","X2_7",
"X2_15"),
measure.vars=c("X2_1","X2_2","X2_3",
"X2_4","X2_5","X2_6","X2_7",
"X2_15"),
variable.name="MediaRichness2", value.name="MRItem2")
MainStudyMelt3<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","X3_1","X3_2","X3_3",
"X3_4","X3_5","X3_6","X3_7",
"X3_15"),
measure.vars=c("X3_1","X3_2","X3_3",
"X3_4","X3_5","X3_6","X3_7",
"X3_15"),
variable.name="MediaRichness3", value.name="MRItem3")
cronbach(cbind(MainStudyMelt1$MRItem1,MainStudyMelt2$MRItem2,MainStudyMelt3$MRItem3)) ## Cronabch 0.81
## $sample.size
## [1] 400
##
## $number.of.items
## [1] 3
##
## $alpha
## [1] 0.8172619
## Reliability Tie Strength
MainStudyMelt4<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","X4_1","X4_2","X4_3",
"X4_4","X4_5","X4_6","X4_7",
"X4_15"),
measure.vars=c("X4_1","X4_2","X4_3",
"X4_4","X4_5","X4_6","X4_7",
"X4_15"),
variable.name="TieStr1", value.name="TieStrItem1")
MainStudyMelt5<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","X5_1","X5_2","X5_3",
"X5_4","X5_5","X5_6","X5_7",
"X5_15"),
measure.vars=c("X5_1","X5_2","X5_3",
"X5_4","X5_5","X5_6","X5_7",
"X5_15"),
variable.name="TieStr2", value.name="TieStrItem2")
cronbach(cbind(MainStudyMelt4$TieStrItem1,MainStudyMelt5$TieStrItem2)) ## Cronabch 0.89
## $sample.size
## [1] 400
##
## $number.of.items
## [1] 2
##
## $alpha
## [1] 0.8946946
validity<-data.frame(cbind(MainStudyMelt1$MRItem1,MainStudyMelt2$MRItem2,MainStudyMelt3$MRItem3,MainStudyMelt4$TieStrItem1,MainStudyMelt5$TieStrItem2))
mardiaTest(validity)
## Mardia's Multivariate Normality Test
## ---------------------------------------
## data : validity
##
## g1p : 2.383954
## chi.skew : 158.9302
## p.value.skew : 1.019388e-17
##
## g2p : 36.6415
## z.kurtosis : 1.961972
## p.value.kurt : 0.04976572
##
## chi.small.skew : 160.5225
## p.value.small : 5.406671e-18
##
## Result : Data are not multivariate normal.
## ---------------------------------------
KMO(validity)
## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = validity)
## Overall MSA = 0.79
## MSA for each item =
## X1 X2 X3 X4 X5
## 0.88 0.82 0.83 0.75 0.73
factanal(validity,2,rotation="varimax")
##
## Call:
## factanal(x = validity, factors = 2, rotation = "varimax")
##
## Uniquenesses:
## X1 X2 X3 X4 X5
## 0.533 0.295 0.309 0.322 0.005
##
## Loadings:
## Factor1 Factor2
## X1 0.636 0.249
## X2 0.800 0.254
## X3 0.694 0.457
## X4 0.384 0.729
## X5 0.309 0.948
##
## Factor1 Factor2
## SS loadings 1.769 1.766
## Proportion Var 0.354 0.353
## Cumulative Var 0.354 0.707
##
## Test of the hypothesis that 2 factors are sufficient.
## The chi square statistic is 0.23 on 1 degree of freedom.
## The p-value is 0.633
summary(prcomp(validity)) ## Two components explain 69% of the variance
## Importance of components%s:
## PC1 PC2 PC3 PC4 PC5
## Standard deviation 4.7071 2.2192 1.57373 1.41028 1.16880
## Proportion of Variance 0.6732 0.1496 0.07525 0.06043 0.04151
## Cumulative Proportion 0.6732 0.8228 0.89807 0.95849 1.00000
screeplot(prcomp(validity),type="lines")
biplot(prcomp(validity,scale.=T),cex=0.5,xlabs=rep(".",nrow(validity)))
rcorr(as.matrix(validity))
## X1 X2 X3 X4 X5
## X1 1.00 0.57 0.56 0.43 0.43
## X2 0.57 1.00 0.67 0.50 0.49
## X3 0.56 0.67 1.00 0.59 0.65
## X4 0.43 0.50 0.59 1.00 0.81
## X5 0.43 0.49 0.65 0.81 1.00
##
## n= 400
##
##
## P
## X1 X2 X3 X4 X5
## X1 0 0 0 0
## X2 0 0 0 0
## X3 0 0 0 0
## X4 0 0 0 0
## X5 0 0 0 0
MainStudy$MRFacebook<-(MainStudy$X3_1+MainStudy$X1_1+MainStudy$X2_1)/3-38
MainStudy$MRTwitter<-(MainStudy$X3_2+MainStudy$X1_2+MainStudy$X2_2)/3-38
MainStudy$MRYouTube<-(MainStudy$X3_3+MainStudy$X1_3+MainStudy$X2_3)/3-38
MainStudy$MRInstagram<-(MainStudy$X3_4+MainStudy$X1_4+MainStudy$X2_4)/3-38
MainStudy$MRPinterest<-(MainStudy$X3_5+MainStudy$X1_5+MainStudy$X2_5)/3-38
MainStudy$MRSnapChat<-(MainStudy$X3_6+MainStudy$X1_6+MainStudy$X2_6)/3-38
MainStudy$MRLinkedIn<-(MainStudy$X3_7+MainStudy$X1_7+MainStudy$X2_7)/3-38
MainStudy$MRSecondLife<-(MainStudy$X3_15+MainStudy$X1_15+MainStudy$X2_15)/3-38
MainStudy$TSFacebook<-(MainStudy$X4_1+MainStudy$X5_1)/2-38
MainStudy$TSTwitter<-(MainStudy$X4_2+MainStudy$X5_2)/2-38
MainStudy$TSYouTube<-(MainStudy$X4_3+MainStudy$X5_3)/2-38
MainStudy$TSInstagram<-(MainStudy$X4_4+MainStudy$X5_4)/2-38
MainStudy$TSPinterest<-(MainStudy$X4_5+MainStudy$X5_5)/2-38
MainStudy$TSSnapChat<-(MainStudy$X4_6+MainStudy$X5_6)/2-38
MainStudy$TSLinkedIn<-(MainStudy$X4_7+MainStudy$X5_7)/2-38
MainStudy$TSSecondLife<-(MainStudy$X4_15+MainStudy$X5_15)/2-38
summary(MainStudy)
## StartDate EndDate Status IPAddress
## 9/28/2017 5:29: 3 9/28/2017 2:26: 2 Min. :0 37.187.147.158: 2
## 9/28/2017 1:44: 2 9/28/2017 3:43: 2 1st Qu.:0 1.22.132.15 : 1
## 9/28/2017 3:20: 2 9/28/2017 5:02: 2 Median :0 103.204.47.33 : 1
## 9/28/2017 4:51: 2 9/28/2017 5:06: 2 Mean :0 103.25.47.134 : 1
## 9/28/2017 5:52: 2 9/28/2017 5:36: 2 3rd Qu.:0 103.88.77.3 : 1
## 9/28/2017 8:30: 2 9/28/2017 1:21: 1 Max. :0 106.51.152.46 : 1
## (Other) :37 (Other) :39 (Other) :43
## Progress Duration..in.seconds. Finished RecordedDate
## Min. :100 Min. : 374.0 Min. :1 9/28/2017 2:26: 2
## 1st Qu.:100 1st Qu.: 424.2 1st Qu.:1 9/28/2017 3:43: 2
## Median :100 Median : 490.0 Median :1 9/28/2017 5:02: 2
## Mean :100 Mean : 582.4 Mean :1 9/28/2017 5:06: 2
## 3rd Qu.:100 3rd Qu.: 634.2 3rd Qu.:1 9/28/2017 5:36: 2
## Max. :100 Max. :1753.0 Max. :1 9/28/2017 1:21: 1
## (Other) :39
## ResponseId RecipientLastName RecipientFirstName
## R_10T8rIxyUdDqUvY: 1 Mode:logical Mode:logical
## R_1BoX1ncuNMXu7TD: 1 NA's:50 NA's:50
## R_1CazBZ3AMwO2Xwb: 1
## R_1f2xJMMytF6btHR: 1
## R_1hALgNb68Qa7d9i: 1
## R_1i2LOTcQ6vqrYPd: 1
## (Other) :44
## RecipientEmail ExternalReference LocationLatitude LocationLongitude
## Mode:logical Mode:logical Min. : 8.00 Min. :-122.68
## NA's:50 NA's:50 1st Qu.:13.08 1st Qu.: -71.70
## Median :15.92 Median : 77.09
## Mean :23.26 Mean : 29.41
## 3rd Qu.:39.12 3rd Qu.: 80.28
## Max. :53.75 Max. : 121.02
##
## DistributionChannel UserLanguage t0_First.Click t0_Last.Click
## anonymous:50 : 2 Min. : 0.000 Min. : 0.000
## EN:48 1st Qu.: 0.000 1st Qu.: 0.000
## Median : 0.000 Median : 0.000
## Mean : 2.289 Mean : 4.524
## 3rd Qu.: 0.000 3rd Qu.: 0.000
## Max. :36.752 Max. :59.745
##
## t0_Page.Submit t0_Click.Count X0B_Browser X0B_Version
## Min. : 15.97 Min. :0.00 Chrome :35 61.0.3163.100:20
## 1st Qu.: 17.50 1st Qu.:0.00 Firefox :12 55 : 8
## Median : 20.49 Median :0.00 Safari : 2 60.0.3112.113: 3
## Mean : 43.52 Mean :0.66 Safari iPad: 1 49.0.2623.112: 2
## 3rd Qu.: 27.98 3rd Qu.:0.00 Chrome iPad: 0 5.1.7 : 2
## Max. :416.32 Max. :9.00 Edge : 0 60.0.3112.90 : 2
## (Other) : 0 (Other) :13
## X0B_Operating.System X0B_Resolution V1 V2
## Windows NT 6.1 :19 1366x768 :19 Min. :10 Min. :9
## Windows NT 10.0:11 1280x800 : 6 1st Qu.:10 1st Qu.:9
## Android 6.0.1 : 3 1280x1024: 5 Median :10 Median :9
## Macintosh : 3 1024x768 : 3 Mean :10 Mean :9
## Windows NT 5.1 : 3 360x640 : 3 3rd Qu.:10 3rd Qu.:9
## Windows NT 6.3 : 3 1440x900 : 2 Max. :10 Max. :9
## (Other) : 8 (Other) :12
## V3 V4 tV_First.Click tV_Last.Click
## Min. : 9.0 4,5,6,7,8,9,10 :13 Min. : 1.250 Min. : 9.257
## 1st Qu.: 9.0 4,5,6,7,8,10 : 6 1st Qu.: 2.507 1st Qu.:17.028
## Median : 9.5 4,5,6 : 4 Median : 3.454 Median :21.335
## Mean : 9.5 4,5,6,7,8,9,10,11: 3 Mean : 4.995 Mean :23.431
## 3rd Qu.:10.0 4 : 2 3rd Qu.: 4.787 3rd Qu.:27.987
## Max. :10.0 4,5,6,10 : 2 Max. :52.247 Max. :69.337
## (Other) :20
## tV_Page.Submit tV_Click.Count X1_1 X1_2
## Min. :10.17 Min. : 4.00 Min. :39.00 Min. :39.00
## 1st Qu.:18.41 1st Qu.: 8.00 1st Qu.:44.00 1st Qu.:43.00
## Median :23.34 Median :10.00 Median :45.00 Median :45.00
## Mean :25.40 Mean :11.18 Mean :44.76 Mean :44.12
## 3rd Qu.:30.00 3rd Qu.:11.00 3rd Qu.:46.00 3rd Qu.:45.75
## Max. :75.09 Max. :32.00 Max. :47.00 Max. :47.00
##
## X1_3 X1_4 X1_5 X1_6
## Min. :40.00 Min. :39.00 Min. :39.0 Min. :39.00
## 1st Qu.:44.00 1st Qu.:43.00 1st Qu.:43.0 1st Qu.:41.25
## Median :45.00 Median :45.00 Median :44.5 Median :43.00
## Mean :45.08 Mean :44.42 Mean :44.1 Mean :43.16
## 3rd Qu.:47.00 3rd Qu.:46.00 3rd Qu.:46.0 3rd Qu.:44.75
## Max. :47.00 Max. :47.00 Max. :47.0 Max. :47.00
##
## X1_7 X1_15 t1_First.Click t1_Last.Click
## Min. :39.00 Min. :39.00 Min. : 0.836 Min. : 4.256
## 1st Qu.:41.00 1st Qu.:41.00 1st Qu.: 4.304 1st Qu.: 21.102
## Median :43.00 Median :43.00 Median : 6.212 Median : 39.944
## Mean :43.14 Mean :42.74 Mean : 7.830 Mean : 43.273
## 3rd Qu.:45.00 3rd Qu.:44.75 3rd Qu.: 8.868 3rd Qu.: 60.008
## Max. :47.00 Max. :47.00 Max. :33.204 Max. :122.232
##
## t1_Page.Submit t1_Click.Count X2_1 X2_2
## Min. : 61.11 Min. : 8.00 Min. :41.00 Min. :39.00
## 1st Qu.: 62.59 1st Qu.: 9.00 1st Qu.:44.00 1st Qu.:42.25
## Median : 65.43 Median :11.50 Median :45.00 Median :44.50
## Mean :103.60 Mean :13.38 Mean :44.82 Mean :43.82
## 3rd Qu.: 84.50 3rd Qu.:17.00 3rd Qu.:46.00 3rd Qu.:45.00
## Max. :981.92 Max. :31.00 Max. :47.00 Max. :47.00
##
## X2_3 X2_4 X2_5 X2_6
## Min. :41.0 Min. :39.00 Min. :39.00 Min. :39.00
## 1st Qu.:45.0 1st Qu.:42.25 1st Qu.:43.00 1st Qu.:40.25
## Median :46.0 Median :44.00 Median :44.50 Median :43.00
## Mean :45.5 Mean :43.80 Mean :43.88 Mean :42.30
## 3rd Qu.:47.0 3rd Qu.:45.00 3rd Qu.:45.75 3rd Qu.:44.00
## Max. :47.0 Max. :47.00 Max. :47.00 Max. :47.00
##
## X2_7 X2_15 Q774_First.Click Q774_Last.Click
## Min. :39.00 Min. :39.00 Min. : 0.692 Min. : 3.404
## 1st Qu.:41.25 1st Qu.:40.25 1st Qu.: 4.062 1st Qu.: 18.695
## Median :43.00 Median :43.00 Median : 7.470 Median : 33.911
## Mean :42.96 Mean :42.34 Mean : 9.889 Mean : 50.221
## 3rd Qu.:45.00 3rd Qu.:44.00 3rd Qu.:12.105 3rd Qu.: 60.494
## Max. :47.00 Max. :47.00 Max. :64.105 Max. :555.504
##
## Q774_Page.Submit Q774_Click.Count X3_1 X3_2
## Min. : 61.16 Min. : 8.00 Min. :39.00 Min. :39.00
## 1st Qu.: 62.66 1st Qu.: 8.00 1st Qu.:43.00 1st Qu.:40.25
## Median : 69.47 Median :11.00 Median :45.00 Median :43.00
## Mean :102.26 Mean :13.22 Mean :44.34 Mean :42.70
## 3rd Qu.:102.92 3rd Qu.:14.75 3rd Qu.:46.00 3rd Qu.:45.00
## Max. :555.58 Max. :50.00 Max. :47.00 Max. :47.00
##
## X3_3 X3_4 X3_5 X3_6
## Min. :39.00 Min. :39.00 Min. :39.00 Min. :39.00
## 1st Qu.:43.00 1st Qu.:41.00 1st Qu.:42.00 1st Qu.:39.00
## Median :45.00 Median :43.00 Median :43.00 Median :41.00
## Mean :44.46 Mean :42.66 Mean :43.18 Mean :41.64
## 3rd Qu.:46.00 3rd Qu.:44.75 3rd Qu.:45.00 3rd Qu.:43.75
## Max. :47.00 Max. :47.00 Max. :47.00 Max. :47.00
##
## X3_7 X3_15 Q776_First.Click Q776_Last.Click
## Min. :39.00 Min. :39.00 Min. : 0.849 Min. : 3.421
## 1st Qu.:40.25 1st Qu.:39.00 1st Qu.: 2.640 1st Qu.: 19.424
## Median :43.00 Median :39.00 Median : 5.031 Median : 30.837
## Mean :42.46 Mean :40.98 Mean : 8.607 Mean : 38.878
## 3rd Qu.:44.00 3rd Qu.:42.75 3rd Qu.: 8.897 3rd Qu.: 59.546
## Max. :47.00 Max. :46.00 Max. :72.620 Max. :116.506
##
## Q776_Page.Submit Q776_Click.Count X4_1 X4_2
## Min. : 61.13 Min. : 8.00 Min. :40.00 Min. :39.00
## 1st Qu.: 62.72 1st Qu.: 8.00 1st Qu.:44.25 1st Qu.:43.00
## Median : 71.14 Median :10.00 Median :46.00 Median :44.00
## Mean : 96.13 Mean :13.22 Mean :45.40 Mean :43.96
## 3rd Qu.: 88.52 3rd Qu.:15.75 3rd Qu.:47.00 3rd Qu.:46.00
## Max. :683.66 Max. :42.00 Max. :47.00 Max. :47.00
##
## X4_3 X4_4 X4_5 X4_6
## Min. :39.00 Min. :39.00 Min. :39.00 Min. :39.00
## 1st Qu.:41.25 1st Qu.:42.25 1st Qu.:40.00 1st Qu.:39.00
## Median :44.00 Median :44.00 Median :42.00 Median :42.00
## Mean :43.46 Mean :43.66 Mean :42.32 Mean :42.12
## 3rd Qu.:45.75 3rd Qu.:46.00 3rd Qu.:44.00 3rd Qu.:44.75
## Max. :47.00 Max. :47.00 Max. :47.00 Max. :47.00
##
## X4_7 X4_15 Q778_First.Click Q778_Last.Click
## Min. :39.00 Min. :39.0 Min. : 0.885 Min. : 4.476
## 1st Qu.:42.25 1st Qu.:39.0 1st Qu.: 4.983 1st Qu.: 27.854
## Median :44.00 Median :40.0 Median : 7.396 Median : 44.758
## Mean :43.80 Mean :41.4 Mean : 9.577 Mean : 46.593
## 3rd Qu.:45.75 3rd Qu.:44.0 3rd Qu.:10.875 3rd Qu.: 60.206
## Max. :47.00 Max. :47.0 Max. :65.250 Max. :121.689
##
## Q778_Page.Submit Q778_Click.Count X5_1 X5_2
## Min. : 61.08 Min. : 8.00 Min. :40.00 Min. :39.00
## 1st Qu.: 61.93 1st Qu.: 9.00 1st Qu.:45.00 1st Qu.:41.25
## Median : 62.95 Median :10.50 Median :46.00 Median :44.00
## Mean : 73.21 Mean :15.24 Mean :45.36 Mean :43.46
## 3rd Qu.: 76.19 3rd Qu.:16.75 3rd Qu.:47.00 3rd Qu.:46.00
## Max. :157.36 Max. :66.00 Max. :47.00 Max. :47.00
##
## X5_3 X5_4 X5_5 X5_6
## Min. :39.00 Min. :39.00 Min. :39.00 Min. :39.00
## 1st Qu.:41.00 1st Qu.:41.00 1st Qu.:39.00 1st Qu.:39.00
## Median :44.00 Median :43.00 Median :42.00 Median :41.50
## Mean :43.18 Mean :42.96 Mean :42.12 Mean :41.96
## 3rd Qu.:45.00 3rd Qu.:45.00 3rd Qu.:44.00 3rd Qu.:44.00
## Max. :47.00 Max. :47.00 Max. :47.00 Max. :47.00
##
## X5_7 X5_15 Q780_First.Click Q780_Last.Click
## Min. :39.00 Min. :39.00 Min. : 0.882 Min. : 5.832
## 1st Qu.:42.00 1st Qu.:39.00 1st Qu.: 4.543 1st Qu.: 32.826
## Median :43.00 Median :40.00 Median : 8.931 Median : 49.100
## Mean :43.34 Mean :40.94 Mean : 9.971 Mean : 52.914
## 3rd Qu.:45.75 3rd Qu.:42.75 3rd Qu.:12.747 3rd Qu.: 62.276
## Max. :47.00 Max. :47.00 Max. :40.273 Max. :196.035
##
## Q780_Page.Submit Q780_Click.Count X3 X4
## Min. : 60.93 Min. : 8.00 Min. :1949 Min. :1.00
## 1st Qu.: 62.53 1st Qu.: 9.00 1st Qu.:1979 1st Qu.:1.00
## Median : 64.97 Median :11.00 Median :1986 Median :3.50
## Mean : 86.12 Mean :15.42 Mean :1982 Mean :3.18
## 3rd Qu.: 75.39 3rd Qu.:16.50 3rd Qu.:1988 3rd Qu.:5.00
## Max. :505.77 Max. :70.00 Max. :1990 Max. :7.00
##
## t3_First.Click t3_Last.Click t3_Page.Submit t3_Click.Count
## Min. : 1.404 Min. : 4.553 Min. : 5.587 Min. : 2.00
## 1st Qu.: 2.312 1st Qu.: 7.345 1st Qu.: 8.748 1st Qu.: 2.00
## Median : 3.377 Median : 8.812 Median : 11.464 Median : 2.00
## Mean : 9.071 Mean : 16.427 Mean : 18.759 Mean : 2.94
## 3rd Qu.: 5.055 3rd Qu.: 16.309 3rd Qu.: 18.027 3rd Qu.: 3.00
## Max. :203.935 Max. :205.335 Max. :208.775 Max. :13.00
##
## X5 X6 X6_6_TEXT t4_First.Click
## Min. : 9.00 Min. :1.00 :38 Min. : 1.254
## 1st Qu.:12.00 1st Qu.:2.00 Indian : 4 1st Qu.: 2.792
## Median :12.00 Median :2.00 asian : 2 Median : 3.466
## Mean :12.06 Mean :3.22 Asian : 2 Mean : 5.989
## 3rd Qu.:13.00 3rd Qu.:4.75 Asian/Indian: 1 3rd Qu.: 4.179
## Max. :15.00 Max. :6.00 Mixed : 1 Max. :71.134
## (Other) : 2
## t4_Last.Click t4_Page.Submit t4_Click.Count mTurkCode
## Min. : 3.004 Min. : 3.834 Min. : 2.00 Min. : 0.00
## 1st Qu.: 5.530 1st Qu.: 7.016 1st Qu.: 2.00 1st Qu.:21.25
## Median : 7.705 Median : 9.520 Median : 2.50 Median :44.00
## Mean :11.190 Mean :16.241 Mean : 3.78 Mean :47.90
## 3rd Qu.:12.505 3rd Qu.:16.907 3rd Qu.: 4.00 3rd Qu.:78.50
## Max. :75.028 Max. :85.504 Max. :16.00 Max. :99.00
##
## MRFacebook MRTwitter MRYouTube MRInstagram
## Min. :2.333 Min. :1.000 Min. :3.667 Min. :2.000
## 1st Qu.:6.000 1st Qu.:4.333 1st Qu.:6.333 1st Qu.:4.333
## Median :6.667 Median :6.000 Median :7.333 Median :6.000
## Mean :6.640 Mean :5.547 Mean :7.013 Mean :5.627
## 3rd Qu.:7.667 3rd Qu.:6.667 3rd Qu.:8.000 3rd Qu.:7.000
## Max. :9.000 Max. :8.333 Max. :9.000 Max. :9.000
##
## MRPinterest MRSnapChat MRLinkedIn MRSecondLife
## Min. :1.667 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:4.000 1st Qu.:2.417 1st Qu.:3.667 1st Qu.:2.417
## Median :6.000 Median :4.333 Median :5.000 Median :3.667
## Mean :5.720 Mean :4.367 Mean :4.853 Mean :4.020
## 3rd Qu.:7.333 3rd Qu.:5.833 3rd Qu.:6.333 3rd Qu.:5.500
## Max. :8.333 Max. :8.667 Max. :8.667 Max. :8.667
##
## TSFacebook TSTwitter TSYouTube TSInstagram
## Min. :2.000 Min. :1.000 Min. :1.000 Min. :1.000
## 1st Qu.:6.625 1st Qu.:4.125 1st Qu.:3.125 1st Qu.:3.625
## Median :7.750 Median :6.000 Median :5.500 Median :5.500
## Mean :7.380 Mean :5.710 Mean :5.320 Mean :5.310
## 3rd Qu.:9.000 3rd Qu.:7.500 3rd Qu.:7.500 3rd Qu.:7.000
## Max. :9.000 Max. :9.000 Max. :9.000 Max. :9.000
##
## TSPinterest TSSnapChat TSLinkedIn TSSecondLife
## Min. :1.00 Min. :1.000 Min. :1.00 Min. :1.000
## 1st Qu.:2.00 1st Qu.:1.625 1st Qu.:4.50 1st Qu.:1.000
## Median :4.00 Median :3.500 Median :5.50 Median :2.250
## Mean :4.22 Mean :4.040 Mean :5.57 Mean :3.170
## 3rd Qu.:6.00 3rd Qu.:6.500 3rd Qu.:7.50 3rd Qu.:4.875
## Max. :9.00 Max. :9.000 Max. :9.00 Max. :8.500
##
t.test(MainStudy$MRYouTube,MainStudy$MRFacebook)
##
## Welch Two Sample t-test
##
## data: MainStudy$MRYouTube and MainStudy$MRFacebook
## t = 1.2293, df = 96.807, p-value = 0.2219
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.2294196 0.9760863
## sample estimates:
## mean of x mean of y
## 7.013333 6.640000
t.test(MainStudy$MRYouTube,MainStudy$MRTwitter)
##
## Welch Two Sample t-test
##
## data: MainStudy$MRYouTube and MainStudy$MRTwitter
## t = 4.5105, df = 93.294, p-value = 1.88e-05
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.8209743 2.1123590
## sample estimates:
## mean of x mean of y
## 7.013333 5.546667
t.test(MainStudy$MRFacebook,MainStudy$MRTwitter) ## Two levels of Content Vividness
##
## Welch Two Sample t-test
##
## data: MainStudy$MRFacebook and MainStudy$MRTwitter
## t = 3.2105, df = 96.688, p-value = 0.001799
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.4174128 1.7692539
## sample estimates:
## mean of x mean of y
## 6.640000 5.546667
mean(MainStudy$MRYouTube)
## [1] 7.013333
sd(MainStudy$MRYouTube)
## [1] 1.431679
mean(MainStudy$MRFacebook)
## [1] 6.64
sd(MainStudy$MRFacebook)
## [1] 1.60051
mean(MainStudy$MRTwitter)
## [1] 5.546667
sd(MainStudy$MRTwitter)
## [1] 1.799168
t.test(MainStudy$TSYouTube,MainStudy$TSFacebook)
##
## Welch Two Sample t-test
##
## data: MainStudy$TSYouTube and MainStudy$TSFacebook
## t = -4.743, df = 83.499, p-value = 8.585e-06
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -2.923775 -1.196225
## sample estimates:
## mean of x mean of y
## 5.32 7.38
t.test(MainStudy$TSYouTube,MainStudy$TSTwitter)
##
## Welch Two Sample t-test
##
## data: MainStudy$TSYouTube and MainStudy$TSTwitter
## t = -0.78715, df = 97.235, p-value = 0.4331
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -1.3733189 0.5933189
## sample estimates:
## mean of x mean of y
## 5.32 5.71
t.test(MainStudy$TSFacebook,MainStudy$TSTwitter) ## Two levels of Tie Str
##
## Welch Two Sample t-test
##
## data: MainStudy$TSFacebook and MainStudy$TSTwitter
## t = 4.0882, df = 87.81, p-value = 9.599e-05
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.8581796 2.4818204
## sample estimates:
## mean of x mean of y
## 7.38 5.71
mean(MainStudy$TSYouTube)
## [1] 5.32
sd(MainStudy$TSYouTube)
## [1] 2.584806
mean(MainStudy$TSFacebook)
## [1] 7.38
sd(MainStudy$TSFacebook)
## [1] 1.658497
mean(MainStudy$TSTwitter)
## [1] 5.71
sd(MainStudy$TSTwitter)
## [1] 2.364901
MainStudyMelt1<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","TSFacebook","TSTwitter","TSYouTube","TSInstagram","TSPinterest","TSSnapChat","TSLinkedIn","TSSecondLife"),measure.vars=c("TSFacebook","TSTwitter","TSYouTube","TSInstagram","TSPinterest","TSSnapChat","TSLinkedIn","TSSecondLife"),variable.name="SMP", value.name="TieStrength")
MainStudyMelt2<-melt(MainStudy,id.vars=c("ResponseId","X3","V3","MRFacebook","MRTwitter","MRYouTube","MRInstagram","MRPinterest","MRSnapChat","MRLinkedIn","MRSecondLife"),measure.vars=c("MRFacebook","MRTwitter","MRYouTube","MRInstagram","MRPinterest","MRSnapChat","MRLinkedIn","MRSecondLife"),variable.name="SMP", value.name="MediaRichness")
MainStudyMelt<-cbind(MainStudyMelt1,MainStudyMelt2)
hist(MainStudyMelt$TieStrength)
plot(density(MainStudyMelt$TieStrength))
screeplot(prcomp(cbind(MainStudyMelt$SMP,MainStudyMelt$TieStrength),type="lines"))
## Warning: In prcomp.default(cbind(MainStudyMelt$SMP, MainStudyMelt$TieStrength),
## type = "lines") :
## extra argument 'type' will be disregarded
summary(prcomp(cbind(MainStudyMelt$SMP,MainStudyMelt$TieStrength)))
## Importance of components%s:
## PC1 PC2
## Standard deviation 2.9096 1.9372
## Proportion of Variance 0.6928 0.3071
## Cumulative Proportion 0.6928 1.0000
## At least two components
mydata<-data.frame(MainStudyMelt$TieStrength)
wss <- (nrow(mydata)-1)*sum(apply(mydata,2,var))
for (i in 2:15) wss[i] <- sum(kmeans(mydata,
centers=i)$withinss)
plot(1:15, wss, type="b", xlab="Number of Clusters",
ylab="Within groups sum of squares")
wss<-wss/sum(wss)*100
for (i in 2:15)
wss[i]<-wss[i]+wss[i-1]
plot(1:15, wss, type="b", xlab="Number of Clusters",
ylab="% Var explained")
wss
## [1] 64.92153 81.23422 87.64483 91.53786 93.91399 95.40564 96.63822
## [8] 97.32955 98.07574 98.64732 99.18572 99.46976 99.69873 99.87468
## [15] 100.00000
## 3 clusters explain more than 80% of the variance
abline(v=3,lty=2)
d <- dist(mydata,method="euclidean") # distance matrix
fit <- hclust(d, method="ward")
## The "ward" method has been renamed to "ward.D"; note new "ward.D2"
plot(fit) # display dendogram all raw data
groups <- cutree(fit,k=3) # cut tree into 3 clusters
rect.hclust(fit,k=3,border="red") # draw dendogram with red borders around the 4 clusters
mydata2<-aggregate(MainStudyMelt$TieStrength,list(MainStudyMelt$SMP),mean)
rownames(mydata2)<-c("Facebook","Twitter","YouTube","Instagram","Pinterest",
"SnapChat","LinkedIn","SecondLife")
d<-dist(mydata2,method="euclidean") # distance matrix
## Warning in dist(mydata2, method = "euclidean"): NAs introduced by coercion
fit <- hclust(d, method="ward")
## The "ward" method has been renamed to "ward.D"; note new "ward.D2"
plot(fit,ylab="Tie strength") # display dendogram mean by SMP
groups <- cutree(fit,k=3) # cut tree into 4 clusters
rect.hclust(fit,k=3,border="red") # draw dendogram with red borders around the 4 clusters
hist(MainStudyMelt$MediaRichness)
plot(density(MainStudyMelt$MediaRichness))
screeplot(prcomp(cbind(MainStudyMelt$SMP,MainStudyMelt$MediaRichness),type="lines"))
## Warning: In prcomp.default(cbind(MainStudyMelt$SMP, MainStudyMelt$MediaRichness),
## type = "lines") :
## extra argument 'type' will be disregarded
summary(prcomp(cbind(MainStudyMelt$SMP,MainStudyMelt$MediaRichness)))
## Importance of components%s:
## PC1 PC2
## Standard deviation 2.5873 1.6883
## Proportion of Variance 0.7014 0.2987
## Cumulative Proportion 0.7014 1.0000
## At least two components
mydata<-data.frame(MainStudyMelt$MediaRichness)
wss <- (nrow(mydata)-1)*sum(apply(mydata,2,var))
for (i in 2:15) wss[i] <- sum(kmeans(mydata,
centers=i)$withinss)
plot(1:15, wss, type="b", xlab="Number of Clusters",
ylab="Within groups sum of squares")
wss<-wss/sum(wss)*100
for (i in 2:15)
wss[i]<-wss[i]+wss[i-1]
plot(1:15, wss, type="b", xlab="Number of Clusters",
ylab="% Var explained")
wss
## [1] 57.56473 72.88376 81.37180 86.12562 89.26672 91.71882 93.25541
## [8] 94.94939 96.17952 96.84776 97.50254 98.42568 99.24339 99.69277
## [15] 100.00000
## 3 clusters explain more than 80% of the variance
abline(v=3,lty=2)
d <- dist(mydata,method="euclidean") # distance matrix
fit <- hclust(d, method="ward")
## The "ward" method has been renamed to "ward.D"; note new "ward.D2"
plot(fit) # display dendogram all raw data
groups <- cutree(fit,k=3) # cut tree into 3 clusters
rect.hclust(fit,k=3,border="red") # draw dendogram with red borders around the 4 clusters
mydata2<-aggregate(MainStudyMelt$MediaRichness,list(MainStudyMelt$SMP),mean)
rownames(mydata2)<-c("Facebook","Twitter","YouTube","Instagram","Pinterest",
"SnapChat","LinkedIn","SecondLife")
d<-dist(mydata2,method="euclidean") # distance matrix
## Warning in dist(mydata2, method = "euclidean"): NAs introduced by coercion
fit <- hclust(d, method="ward")
## The "ward" method has been renamed to "ward.D"; note new "ward.D2"
plot(fit,ylab="Content vividness") # display dendogram mean by SMP
groups <- cutree(fit,k=3) # cut tree into 4 clusters
rect.hclust(fit,k=3,border="red") # draw dendogram with red borders around the 4 clusters
## STUDY 1 (SECONDARY DATA)
cat("\014") # cleans screen
rm(list=ls(all=TRUE)) # remove variables in working memory
setwd("C:/Users/Erik Ernesto Vazquez/Documents") # sets working directory
X<-read.csv("E-Retailer.csv", skip=0, header=T) # reads raw data from Qualtrics
X<-subset(X,X$Merchandise.Category=="Apparel/Accessories"|
X$Merchandise.Category=="Computers/Electronics"|
X$Merchandise.Category=="Health/Beauty")
X$ProdCat<-ifelse(X$Merchandise.Category=="Computers/Electronics","Search",
ifelse(X$Merchandise.Category=="Apparel/Accessories","Experience",
"Credence"))
X$ProdCatLvl<-ifelse(X$Merchandise.Category=="Computers/Electronics",3,
ifelse(X$Merchandise.Category=="Apparel/Accessories",2,
1))
X$WebOnly<-ifelse(X$Merchant.Type=="Web Only",1,0)
X$RetailChain<-ifelse(X$Merchant.Type=="Retail Chain",1,0)
X$ConsumerBM<-ifelse(X$Merchant.Type=="Consumer Brand Manufacturer",1,0)
X$CatalogCallCenter<-ifelse(X$Merchant.Type=="Catallog/Call Center",1,0)
X$ConsistencyLvl<-ifelse(X$Consistency=="Poor",1,
ifelse(X$Consistency=="Fair",2,
ifelse(X$Consistency=="Good",3,
4)))
X$PersonalizationBinary<-ifelse(X$Personalization=="",0,1)
X$ConsistencyLvl<-ifelse(X$Consistency=="Poor",1,
ifelse(X$Consistency=="Fair",2,
ifelse(X$Consistency=="Good",3,
4)))
X$Mobile.Commerce.PlatformBinary<-ifelse(X$Mobile.Commerce.Platform=="",0,1)
X$X2011.Monthly.Visits<-X$X2011.Monthly.Visits*12
table(X$Merchandise.Category)
##
## Apparel/Accessories Automotive Parts/Accessories
## 139 0
## Books/Music/Video Computers/Electronics
## 0 48
## Flowers/Gifts Food/Drug
## 0 0
## Hardware/Home Improvement Health/Beauty
## 0 29
## Housewares/Home Furnishings Jewelry
## 0 0
## Mass Merchant Office Supplies
## 0 0
## Specialty/Non-Apparel Sporting Goods
## 0 0
## Toys/Hobbies
## 0
count(X,c("Merchandise.Category","Merchant.Type"))
## Merchandise.Category Merchant.Type freq
## 1 Apparel/Accessories Catalog/Call Center 17
## 2 Apparel/Accessories Consumer Brand Manufacturer 34
## 3 Apparel/Accessories Retail Chain 60
## 4 Apparel/Accessories Web Only 28
## 5 Computers/Electronics Catalog/Call Center 7
## 6 Computers/Electronics Consumer Brand Manufacturer 12
## 7 Computers/Electronics Retail Chain 9
## 8 Computers/Electronics Web Only 20
## 9 Health/Beauty Catalog/Call Center 3
## 10 Health/Beauty Consumer Brand Manufacturer 3
## 11 Health/Beauty Retail Chain 7
## 12 Health/Beauty Web Only 16
count(X,c("Merchandise.Category","Mobile.Commerce.PlatformBinary"))
## Merchandise.Category Mobile.Commerce.PlatformBinary freq
## 1 Apparel/Accessories 0 95
## 2 Apparel/Accessories 1 44
## 3 Computers/Electronics 0 39
## 4 Computers/Electronics 1 9
## 5 Health/Beauty 0 15
## 6 Health/Beauty 1 14
aggregate(X$X2011.Monthly.Visits,list(X$Merchandise.Category),mean)
## Group.1 x
## 1 Apparel/Accessories 43070925
## 2 Computers/Electronics 183258367
## 3 Health/Beauty 27888090
aggregate(X$X2011.Monthly.Visits,list(X$Merchandise.Category),sd)
## Group.1 x
## 1 Apparel/Accessories 59335237
## 2 Computers/Electronics 868808208
## 3 Health/Beauty 64033836
fit<-(lm(log(X2011.Monthly.Visits)~ProdCatLvl+WebOnly+RetailChain+
ConsumerBM+ConsistencyLvl+PersonalizationBinary+
Mobile.Commerce.PlatformBinary,X))
summary(fit) ## H1a Not supported
##
## Call:
## lm(formula = log(X2011.Monthly.Visits) ~ ProdCatLvl + WebOnly +
## RetailChain + ConsumerBM + ConsistencyLvl + PersonalizationBinary +
## Mobile.Commerce.PlatformBinary, data = X)
##
## Residuals:
## Min 1Q Median 3Q Max
## -3.6626 -0.7814 0.0634 0.6329 5.3404
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 15.11536 0.47769 31.643 < 2e-16 ***
## ProdCatLvl 0.27987 0.14933 1.874 0.062307 .
## WebOnly -0.23732 0.29320 -0.809 0.419202
## RetailChain 0.72994 0.28390 2.571 0.010835 *
## ConsumerBM 0.47927 0.30414 1.576 0.116585
## ConsistencyLvl 0.18510 0.07134 2.594 0.010149 *
## PersonalizationBinary 0.14626 0.17718 0.825 0.410034
## Mobile.Commerce.PlatformBinary 0.72733 0.19239 3.780 0.000205 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.264 on 208 degrees of freedom
## Multiple R-squared: 0.1904, Adjusted R-squared: 0.1632
## F-statistic: 6.988 on 7 and 208 DF, p-value: 1.749e-07
aggregate(X$X2011.Conversion.Rate,list(X$Merchandise.Category),mean)
## Group.1 x
## 1 Apparel/Accessories 0.02956835
## 2 Computers/Electronics 0.02250000
## 3 Health/Beauty 0.05655172
aggregate(X$X2011.Conversion.Rate,list(X$Merchandise.Category),sd)
## Group.1 x
## 1 Apparel/Accessories 0.01735689
## 2 Computers/Electronics 0.01344809
## 3 Health/Beauty 0.03819834
fit<-(lm(X2011.Conversion.Rate~ProdCatLvl+WebOnly+RetailChain+
ConsumerBM+ConsistencyLvl+PersonalizationBinary+
Mobile.Commerce.PlatformBinary,X))
summary(fit) ## H1b Approved
##
## Call:
## lm(formula = X2011.Conversion.Rate ~ ProdCatLvl + WebOnly + RetailChain +
## ConsumerBM + ConsistencyLvl + PersonalizationBinary + Mobile.Commerce.PlatformBinary,
## data = X)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.045984 -0.009485 -0.003161 0.007115 0.103892
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.089544 0.007047 12.708 < 2e-16 ***
## ProdCatLvl -0.015505 0.002203 -7.039 2.77e-11 ***
## WebOnly -0.017721 0.004325 -4.097 5.99e-05 ***
## RetailChain -0.029782 0.004188 -7.111 1.81e-11 ***
## ConsumerBM -0.028788 0.004486 -6.417 9.24e-10 ***
## ConsistencyLvl -0.001202 0.001052 -1.142 0.255
## PersonalizationBinary -0.003177 0.002614 -1.215 0.226
## Mobile.Commerce.PlatformBinary 0.004473 0.002838 1.576 0.117
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.01865 on 208 degrees of freedom
## Multiple R-squared: 0.3628, Adjusted R-squared: 0.3413
## F-statistic: 16.92 on 7 and 208 DF, p-value: < 2.2e-16