reading data
test.df = read.csv("SubAdvData.csv")
attach(test.df)
Q.1a Write R code to display the following output regarding the number of restaurants
tab1 <- table(adType,restaurantType)
addmargins(tab1,c(1,2))
## restaurantType
## adType chain independent Sum
## Curr Ads 2023 2972 4995
## New Ads 1958 3010 4968
## No Ads 2003 3034 5037
## Sum 5984 9016 15000
Q.1b Write R code to display the following output regarding the percentages of restaurants
prop_table <- prop.table(tab1)
round(prop_table,2)
## restaurantType
## adType chain independent
## Curr Ads 0.13 0.20
## New Ads 0.13 0.20
## No Ads 0.13 0.20
Q.1c Write R code to display the following output regarding average number of reservations
aggregate(reservations, by= list(restaurantType),mean)
## Group.1 x
## 1 chain 42.58205
## 2 independent 32.50688
Q.1d Write R code to display the following output regarding average number of reservations
aggregate(reservations, by= list(adType),mean)
## Group.1 x
## 1 Curr Ads 34.03283
## 2 New Ads 41.62762
## 3 No Ads 33.96724
Q 2a
cor(reservations, phoneCalls, method ="pearson")
## [1] 0.6516813
cor(reservations, phoneCalls, method ="spearman")
## [1] 0.6628822
Q 2b
cor.test(reservations, phoneCalls, method = "pearson")
##
## Pearson's product-moment correlation
##
## data: reservations and 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
Q 2c
prop.test(x = 4995 , n = 15000 ,p = 0.4, correct = FALSE)
##
## 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
Q 2d
res <-t.test(reservations, mu = 40.00)
res
##
## One Sample t-test
##
## data: reservations
## t = -53.711, df = 14999, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 40
## 95 percent confidence interval:
## 36.39943 36.65297
## sample estimates:
## mean of x
## 36.5262
Q 2 e
ReservationChain <- subset(test.df,
restaurantType=="chain",select = reservations)
ReservationIndependent <- subset(test.df,
restaurantType=="independent",select = reservations)
tst <- t.test(ReservationChain, ReservationIndependent, var.equal = TRUE)
tst
##
## Two Sample t-test
##
## data: ReservationChain and ReservationIndependent
## 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