#setwd("C:/Users/zxu3/Documents/R/ab_testing")
#Please install the following package if the package "readr" is not installed.
#install.packages("readr")
library(readr)
data <- read_csv("ab_testing.csv")

## Rows: 80 Columns: 2
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (2): Ads, Purchase
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

ls(data) # list the variables in the dataset

## [1] "Ads"      "Purchase"

head(data) #list the first 6 rows of the dataset

## # A tibble: 6 × 2
##     Ads Purchase
##   <dbl>    <dbl>
## 1     1      152
## 2     0       21
## 3     3       77
## 4     0       65
## 5     1      183
## 6     1       87

# creating the factor variable
data$Ads <- factor(data$Ads)
is.factor(data$Ads)

## [1] TRUE

# showing the first 15 rows of the variable "Ads"
data$Ads[1:15]

##  [1] 1 0 3 0 1 1 2 2 2 0 3 3 0 2 3
## Levels: 0 1 2 3

#now we do the regression analysis and examine the results
summary(lm(Purchase~Ads, data = data))

## 
## Call:
## lm(formula = Purchase ~ Ads, data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -50.095 -27.891  -0.227  24.773  65.905 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   55.381      6.472   8.557 9.41e-13 ***
## Ads1          75.714      9.152   8.273 3.31e-12 ***
## Ads2          36.557      9.842   3.715 0.000386 ***
## Ads3          -2.654      9.048  -0.293 0.770096    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 29.66 on 76 degrees of freedom
## Multiple R-squared:  0.5624, Adjusted R-squared:  0.5452 
## F-statistic: 32.56 on 3 and 76 DF,  p-value: 1.216e-13