Term paper

library(readxl)
webinarium <- read_excel("webinarium.xlsx")
str(webinarium)

## Classes 'tbl_df', 'tbl' and 'data.frame':    82 obs. of  8 variables:
##  $ student       : chr  "Айлана Смагулова" "Алина Аухадиева " "Алина Климентьева" "Алина Морозова" ...
##  $ scores1_max31 : num  7 0 9 5 9 3 11 9 12 12 ...
##  $ quizlet       : chr  "yes" "no" "yes" "yes" ...
##  $ nastavnik     : chr  "Лина Сергиенко" "Дмитрий Бушин" "Даша Фрасова" "Дарья Курбанова" ...
##  $ scores2_max31 : num  29 23 24 13 17 15 25 24 28 24 ...
##  $ perindex      : num  22 23 15 8 8 12 14 15 16 12 ...
##  $ testsavg_max31: num  21 25 17 16 19.5 22.5 26 14 0 19 ...
##  $ openavg_max25 : num  16 13 10 5 8.5 10 11 15 0 10.5 ...

webinarium$perindex[webinarium$quizlet == "no"] <- webinarium$perindex[webinarium$quizlet == "no"] * 1.41
webinarium$testsavg_max31[webinarium$quizlet == "no"] <- webinarium$testsavg_max31[webinarium$quizlet == "no"] * 1.41
webinarium$openavg_max25[webinarium$quizlet == "no"] <- webinarium$openavg_max25[webinarium$quizlet == "no"] * 1.41
webinarium$perindex[webinarium$quizlet == "yes"] <- webinarium$perindex[webinarium$quizlet == "yes"] * 0.77
webinarium$testsavg_max31[webinarium$quizlet == "yes"] <- webinarium$testsavg_max31[webinarium$quizlet == "yes"] * 0.77
webinarium$openavg_max25[webinarium$quizlet == "yes"] <- webinarium$openavg_max25[webinarium$quizlet == "yes"] * 0.77

library(ggplot2)
ggplot(webinarium, aes(y = perindex, x = quizlet)) + 
  geom_boxplot(fill = c("skyblue", "salmon")) +
  stat_summary(fun.y = mean, geom = "point", shape = 4, size = 4) +
  theme_classic() 

ggplot(webinarium, aes(y = testsavg_max31, x = quizlet)) + 
  geom_boxplot(fill = c("skyblue", "salmon")) +
  stat_summary(fun.y = mean, geom = "point", shape = 4, size = 4) +
  theme_classic() 

ggplot(webinarium, aes(y = openavg_max25, x = quizlet)) + 
  geom_boxplot(fill = c("skyblue", "salmon")) +
  stat_summary(fun.y = mean, geom = "point", shape = 4, size = 4) +
  theme_classic() 

tper <- t.test(perindex~quizlet, data=webinarium)
tper

## 
##  Welch Two Sample t-test
## 
## data:  perindex by quizlet
## t = 5.4204, df = 36.945, p-value = 3.842e-06
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##   5.829307 12.789561
## sample estimates:
##  mean in group no mean in group yes 
##          21.15000          11.84057

tnotopen <- t.test(testsavg_max31~quizlet, data=webinarium)
tnotopen

## 
##  Welch Two Sample t-test
## 
## data:  testsavg_max31 by quizlet
## t = 6.9508, df = 37.05, p-value = 3.274e-08
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##   9.312979 16.976045
## sample estimates:
##  mean in group no mean in group yes 
##          28.37017          15.22566

topen <- t.test(openavg_max25~quizlet, data=webinarium)
topen

## 
##  Welch Two Sample t-test
## 
## data:  openavg_max25 by quizlet
## t = 4.8072, df = 37.819, p-value = 2.444e-05
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##   4.30239 10.56382
## sample estimates:
##  mean in group no mean in group yes 
##          17.55207          10.11896