library(psych)
library(corrplot)
## corrplot 0.84 loaded
setwd("d:/IIML/Term 5/DAM/")
df<-read.csv("SubAdvData.csv")
addmargins(table(df$adType,df$restaurantType),margin = c(1,2))
##
## chain independent Sum
## Curr Ads 2023 2972 4995
## New Ads 1958 3010 4968
## No Ads 2003 3034 5037
## Sum 5984 9016 15000
round(prop.table(table(df$adType,df$restaurantType)),2)
##
## chain independent
## Curr Ads 0.13 0.20
## New Ads 0.13 0.20
## No Ads 0.13 0.20
aggregate(df$reservations,by=list(df$restaurantType),mean)
## Group.1 x
## 1 chain 42.58205
## 2 independent 32.50688
aggregate(df$reservations,by=list(df$adType),mean)
## Group.1 x
## 1 Curr Ads 34.03283
## 2 New Ads 41.62762
## 3 No Ads 33.96724
cor(df$reservations,df$phoneCalls)
## [1] 0.6516813
cor.test(df$reservations,df$phoneCalls,method = "pearson")
##
## Pearson's product-moment correlation
##
## data: df$reservations and df$phoneCalls
## t = 105.22, df = 14998, p-value < 2.2e-16
## alternative hypothesis: true correlation is not equal to 0
## 95 percent confidence interval:
## 0.6423774 0.6607932
## sample estimates:
## cor
## 0.6516813
prop.test(x=4995,n=15000,p=0.4,correct = F)
##
## 1-sample proportions test without continuity correction
##
## data: 4995 out of 15000, null probability 0.4
## X-squared = 280.56, df = 1, p-value < 2.2e-16
## alternative hypothesis: true p is not equal to 0.4
## 95 percent confidence interval:
## 0.3255016 0.3405839
## sample estimates:
## p
## 0.333
mean(df$reservations)
## [1] 36.5262
s1=subset(df,restaurantType=="chain",select=reservations)
s2=subset(df,restaurantType=="independent",select=reservations)
t.test(s1,s2,var.equal = T)
##
## Two Sample t-test
##
## data: s1 and s2
## t = 97.503, df = 14998, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 9.872633 10.277718
## sample estimates:
## mean of x mean of y
## 42.58205 32.50688