#install.packages("readr")
library(readr)
data <- read_csv("abtesting.csv")
## Parsed with column specification:
## cols(
## Ads = col_double(),
## Purchase = col_double()
## )
ls(data) # list the variables in the dataset
## [1] "Ads" "Purchase"
head(data) #list the first 6 rows of the dataset
## # A tibble: 6 x 2
## Ads Purchase
## <dbl> <dbl>
## 1 1 113
## 2 0 83
## 3 0 52
## 4 1 119
## 5 1 188
## 6 0 99
# 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 0 1 1 0 0 1 1 1 0 0 0 1 0
## Levels: 0 1
#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
## -57.000 -23.250 3.071 22.643 51.000
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 95.429 6.441 14.816 < 2e-16 ***
## Ads1 41.571 9.630 4.317 0.000118 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 29.52 on 36 degrees of freedom
## Multiple R-squared: 0.3411, Adjusted R-squared: 0.3228
## F-statistic: 18.64 on 1 and 36 DF, p-value: 0.0001184
#now we do an analysis for a predictor with 4 different levels
display <- read_csv("abtesting.csv")
## Parsed with column specification:
## cols(
## Ads = col_double(),
## Purchase = col_double()
## )
ls(display) # list the variables in the dataset
## [1] "Ads" "Purchase"
head(display)
## # A tibble: 6 x 2
## Ads Purchase
## <dbl> <dbl>
## 1 1 113
## 2 0 83
## 3 0 52
## 4 1 119
## 5 1 188
## 6 0 99
# creating the factor variable
display$Ads <- factor(display$Ads)
is.factor(display$Ads)
## [1] TRUE
# showing the first 15 rows of the variable "Ads"
display$Ads[1:15]
## [1] 1 0 0 1 1 0 0 1 1 1 0 0 0 1 0
## Levels: 0 1
#now we do a regression analysis for a predictor with 4 different levels
summary(lm(Purchase~Ads, data = display))
##
## Call:
## lm(formula = Purchase ~ Ads, data = display)
##
## Residuals:
## Min 1Q Median 3Q Max
## -57.000 -23.250 3.071 22.643 51.000
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 95.429 6.441 14.816 < 2e-16 ***
## Ads1 41.571 9.630 4.317 0.000118 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 29.52 on 36 degrees of freedom
## Multiple R-squared: 0.3411, Adjusted R-squared: 0.3228
## F-statistic: 18.64 on 1 and 36 DF, p-value: 0.0001184