## Step 1 ; Load the data set
abtest<-read.csv("C:\\Users\\admin\\Desktop\\Statistical computing 1\\Data\\abtest.csv")
mean(abtest$time_spent_on_the_page,na.rm=TRUE)
## [1] 5.3778
median(abtest$time_spent_on_the_page)
## [1] 5.415
sd(abtest$time_spent_on_the_page)
## [1] 2.378166
range(abtest$time_spent_on_the_page)
## [1] 0.19 10.71
IQR(abtest$time_spent_on_the_page)
## [1] 3.1425
max(abtest$time_spent_on_the_page)
## [1] 10.71
min(abtest$time_spent_on_the_page)
## [1] 0.19
table(abtest$time_spent_on_the_page)
##
## 0.19 0.22 0.4 0.91 0.93 1.44 1.65 1.81 1.92 2.08 2.23 2.58 2.66
## 1 1 2 1 1 1 1 1 1 1 1 1 1
## 2.9 3.02 3.05 3.13 3.21 3.3 3.48 3.52 3.65 3.68 3.88 3.91 4.05
## 1 1 1 1 1 1 1 1 1 1 2 1 1
## 4.18 4.28 4.3 4.39 4.4 4.46 4.52 4.68 4.71 4.75 4.87 4.94 5.08
## 1 1 1 1 1 1 1 1 1 2 1 1 1
## 5.15 5.25 5.26 5.28 5.37 5.39 5.4 5.41 5.42 5.47 5.65 5.74 5.86
## 1 1 1 1 1 1 1 1 1 1 1 1 2
## 5.96 6.01 6.03 6.04 6.18 6.2 6.21 6.27 6.41 6.47 6.52 6.53 6.57
## 1 1 1 2 1 1 1 1 1 1 1 1 1
## 6.6 6.7 6.71 6.79 7.02 7.03 7.07 7.13 7.16 7.23 7.27 7.4 7.46
## 1 1 1 1 1 1 1 1 2 1 1 1 1
## 7.81 8.02 8.08 8.3 8.35 8.46 8.47 8.5 8.72 8.73 9.12 9.15 9.49
## 1 1 1 1 1 1 1 1 1 1 1 1 1
## 10.3 10.5 10.71
## 1 1 1
prop.table(abtest$time_spent_on_the_page)
## [1] 0.0064710476 0.0132582097 0.0081817844 0.0056156793 0.0088326081
## [6] 0.0098181412 0.0097623564 0.0121425118 0.0199152070 0.0038677526
## [11] 0.0115474729 0.0047975008 0.0108966492 0.0112127636 0.0162148090
## [16] 0.0116590427 0.0162334040 0.0007437986 0.0191528134 0.0072148462
## [21] 0.0049462606 0.0130722600 0.0067871620 0.0130536651 0.0114916881
## [26] 0.0081631894 0.0176466213 0.0075309606 0.0145226673 0.0079586448
## [31] 0.0100598758 0.0065454275 0.0100226859 0.0084049239 0.0082933542
## [36] 0.0158057198 0.0058202239 0.0112313585 0.0030681691 0.0003533043
## [41] 0.0157313400 0.0035702332 0.0133139946 0.0133139946 0.0072706311
## [46] 0.0149131615 0.0099854959 0.0134441593 0.0150247313 0.0195247127
## [51] 0.0004090892 0.0105061549 0.0120309420 0.0087582283 0.0119193722
## [56] 0.0017293317 0.0033656886 0.0154338205 0.0137602737 0.0170143925
## [61] 0.0111755737 0.0126259809 0.0077726952 0.0101714456 0.0110825988
## [66] 0.0135185392 0.0122726766 0.0088326081 0.0124586262 0.0041466771
## [71] 0.0007437986 0.0100784708 0.0094462420 0.0138718435 0.0090557477
## [76] 0.0122168917 0.0026776749 0.0072148462 0.0169586076 0.0059689836
## [81] 0.0087024434 0.0097809513 0.0106735096 0.0053925397 0.0079958347
## [86] 0.0016921418 0.0124772212 0.0068429469 0.0061363383 0.0112313585
## [91] 0.0100412808 0.0157499349 0.0155267953 0.0091859125 0.0056714642
## [96] 0.0095764067 0.0121239168 0.0131466399 0.0115288780 0.0108966492
##load the required package ``{r} library(ggplot2) library(dplyr) library(readr) library(stats) library(tidyverse)
## ploting
``` r
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.5.2
## Plotting
# Histogram
ggplot(abtest, aes(x = time_spent_on_the_page)) +
geom_histogram()
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
# Boxplot comparing time spent by landing page
ggplot(abtest, aes(x = landing_page, y = time_spent_on_the_page)) +
geom_boxplot()
# Density plot
ggplot(abtest, aes(x = time_spent_on_the_page)) +
geom_density()
# Bar plot (counts of landing_page instead of continuous time)
ggplot(abtest, aes(x = landing_page)) +
geom_bar()