library(readxl)
Data <- read_excel("D:/MARV BS MATH/Marv 3rd year 2nd sem/Statistical Software/Data.xlsx")
View(Data)library(rmarkdown)
paged_table(Data)library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionData<-Data%>%
mutate(In1.1=recode(`In1`,
"1" = "Strongly Disagree", "2" ="Disagree", "3" = "Moderately Disagree", "4" = "Neutral", "5"="Agree", "6" = "Strongly Agree", "7" = "Moderately Agree"))%>%
mutate(In2.1=recode(`In2`,
"1" = "Strongly Disagree", "2" ="Disagree", "3" = "Moderately Disagree", "4" = "Neutral", "5"="Agree", "6" = "Strongly Agree", "7" = "Moderately Agree"))Data$In1=as.numeric(Data$In1)
Data$In2=as.numeric(Data$In2)
Data$In3=as.numeric(Data$In3)
Data$In4=as.numeric(Data$In4)
Data$In5=as.numeric(Data$In5)Data$InAverage<-Data$In1+Data$In2+Data$In3+Data$In4+Data$In5Data## # A tibble: 163 x 36
## Age Gender `Course Taken` In1 In2 In3 In4 In5 In6 In7 In8
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 22 Female BS Mathematics 4 3 2 1 4 7 6 7
## 2 23 Female BS Biology 6 6 4 4 4 5 4 7
## 3 20 Female BSED English 5 5 3 3 2 6 5 7
## 4 22 Female BSED Biology 4 5 4 3 3 6 6 7
## 5 23 Male BSED English 7 6 5 5 4 6 4 7
## 6 22 Female BSED Biology 6 6 6 6 6 7 7 7
## 7 20 Male BS Civil Engine~ 4 5 6 2 5 7 4 1
## 8 21 Female BS Electrical E~ 5 6 5 6 5 7 6 7
## 9 21 Female BS Mathematics 6 7 5 5 5 7 7 7
## 10 22 Male BS Biology 6 7 5 6 7 7 7 7
## # ... with 153 more rows, and 25 more variables: Ex1 <dbl>, Ex2 <dbl>,
## # Ex3 <dbl>, Ex4 <dbl>, Ex5 <dbl>, Ex6 <dbl>, Ex7 <dbl>, Ex8 <dbl>,
## # Ex9 <dbl>, Ex10 <dbl>, Ex11 <dbl>, TP1 <dbl>, TP2 <dbl>, TP3 <dbl>,
## # TP4 <dbl>, TP5 <dbl>, T6 <dbl>, CP1 <dbl>, CP2 <dbl>, CP3 <dbl>, CP4 <dbl>,
## # CP5 <dbl>, In1.1 <chr>, In2.1 <chr>, InAverage <dbl>Data<-Data%>%
mutate(`Group 1` = ifelse(InAverage<=19,"Less than 20 years old",
ifelse(InAverage>=21, "More than 20 years old", "Normal")))%>%
mutate(`Group 2` = ifelse(Age<=20, "19 years old and below", "at most 20 years old"))summary(Data$Age)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 20.00 21.00 22.00 21.56 22.00 25.00library(dplyr)
Data%>%
group_by(`Course Taken`, `Age`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'Course Taken'. You can override using the
## `.groups` argument.## # A tibble: 23 x 4
## # Groups: Course Taken [6]
## `Course Taken` Age count Percentage
## <chr> <dbl> <int> <dbl>
## 1 BS Biology 20 3 0.0909
## 2 BS Biology 21 10 0.303
## 3 BS Biology 22 18 0.545
## 4 BS Biology 23 2 0.0606
## 5 BS Civil Engineering 20 2 0.125
## 6 BS Civil Engineering 21 5 0.312
## 7 BS Civil Engineering 22 9 0.562
## 8 BS Electrical Engineering 21 8 0.471
## 9 BS Electrical Engineering 22 8 0.471
## 10 BS Electrical Engineering 23 1 0.0588
## # ... with 13 more rowsData%>%
group_by(`Course Taken`)%>%
summarise(Frequency=n(), 'Mean Age' = mean(Age))## # A tibble: 6 x 3
## `Course Taken` Frequency `Mean Age`
## <chr> <int> <dbl>
## 1 BS Biology 33 21.6
## 2 BS Civil Engineering 16 21.4
## 3 BS Electrical Engineering 17 21.6
## 4 BS Mathematics 33 21.7
## 5 BSED Biology 32 21.5
## 6 BSED English 32 21.6Data%>%
group_by(`Age`, `InAverage`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'Age'. You can override using the `.groups`
## argument.## # A tibble: 61 x 4
## # Groups: Age [5]
## Age InAverage count Percentage
## <dbl> <dbl> <int> <dbl>
## 1 20 12 1 0.0714
## 2 20 18 1 0.0714
## 3 20 19 1 0.0714
## 4 20 22 2 0.143
## 5 20 24 1 0.0714
## 6 20 26 1 0.0714
## 7 20 27 3 0.214
## 8 20 28 2 0.143
## 9 20 33 1 0.0714
## 10 20 34 1 0.0714
## # ... with 51 more rowslibrary(dplyr)
Data%>%
group_by(`Course Taken`)%>%
summarise(Frequency=n(), 'Mean Intrinsic5' = mean(In5), 'Mean Extrinsic4' = mean(Ex4), 'Mean TP3' = mean(TP3), 'Mean CP2' = mean(CP2))## # A tibble: 6 x 6
## `Course Taken` Frequency `Mean Intrinsi~` `Mean Extrinsi~` `Mean TP3`
## <chr> <int> <dbl> <dbl> <dbl>
## 1 BS Biology 33 4.64 5.67 3.88
## 2 BS Civil Engineering 16 4.56 6.06 3.31
## 3 BS Electrical Engineer~ 17 4.53 5.59 3.47
## 4 BS Mathematics 33 4.52 5.64 3.55
## 5 BSED Biology 32 4.47 5.56 3.25
## 6 BSED English 32 4.41 5.56 3.91
## # ... with 1 more variable: `Mean CP2` <dbl>Data%>%
group_by(`Course Taken`)%>%
summarise(Frequency=n(), 'Mean Intrinsic5' = mean(In5), 'Mean Extrinsic4' = mean(Ex4), 'Mean TP3' = mean(TP3), 'Mean CP2' = mean(CP2))## # A tibble: 6 x 6
## `Course Taken` Frequency `Mean Intrinsi~` `Mean Extrinsi~` `Mean TP3`
## <chr> <int> <dbl> <dbl> <dbl>
## 1 BS Biology 33 4.64 5.67 3.88
## 2 BS Civil Engineering 16 4.56 6.06 3.31
## 3 BS Electrical Engineer~ 17 4.53 5.59 3.47
## 4 BS Mathematics 33 4.52 5.64 3.55
## 5 BSED Biology 32 4.47 5.56 3.25
## 6 BSED English 32 4.41 5.56 3.91
## # ... with 1 more variable: `Mean CP2` <dbl>Data## # A tibble: 163 x 38
## Age Gender `Course Taken` In1 In2 In3 In4 In5 In6 In7 In8
## <dbl> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 22 Female BS Mathematics 4 3 2 1 4 7 6 7
## 2 23 Female BS Biology 6 6 4 4 4 5 4 7
## 3 20 Female BSED English 5 5 3 3 2 6 5 7
## 4 22 Female BSED Biology 4 5 4 3 3 6 6 7
## 5 23 Male BSED English 7 6 5 5 4 6 4 7
## 6 22 Female BSED Biology 6 6 6 6 6 7 7 7
## 7 20 Male BS Civil Engine~ 4 5 6 2 5 7 4 1
## 8 21 Female BS Electrical E~ 5 6 5 6 5 7 6 7
## 9 21 Female BS Mathematics 6 7 5 5 5 7 7 7
## 10 22 Male BS Biology 6 7 5 6 7 7 7 7
## # ... with 153 more rows, and 27 more variables: Ex1 <dbl>, Ex2 <dbl>,
## # Ex3 <dbl>, Ex4 <dbl>, Ex5 <dbl>, Ex6 <dbl>, Ex7 <dbl>, Ex8 <dbl>,
## # Ex9 <dbl>, Ex10 <dbl>, Ex11 <dbl>, TP1 <dbl>, TP2 <dbl>, TP3 <dbl>,
## # TP4 <dbl>, TP5 <dbl>, T6 <dbl>, CP1 <dbl>, CP2 <dbl>, CP3 <dbl>, CP4 <dbl>,
## # CP5 <dbl>, In1.1 <chr>, In2.1 <chr>, InAverage <dbl>, `Group 1` <chr>,
## # `Group 2` <chr>library(dplyr)
Data%>%
group_by(`In1`, `In2`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'In1'. You can override using the `.groups`
## argument.## # A tibble: 27 x 4
## # Groups: In1 [7]
## In1 In2 count Percentage
## <dbl> <dbl> <int> <dbl>
## 1 1 1 2 0.4
## 2 1 3 1 0.2
## 3 1 4 1 0.2
## 4 1 7 1 0.2
## 5 2 2 1 0.25
## 6 2 3 1 0.25
## 7 2 5 2 0.5
## 8 3 3 1 0.167
## 9 3 5 4 0.667
## 10 3 7 1 0.167
## # ... with 17 more rowsData%>%
group_by(`In1`, `In2`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'In1'. You can override using the `.groups`
## argument.## # A tibble: 27 x 4
## # Groups: In1 [7]
## In1 In2 count Percentage
## <dbl> <dbl> <int> <dbl>
## 1 1 1 2 0.4
## 2 1 3 1 0.2
## 3 1 4 1 0.2
## 4 1 7 1 0.2
## 5 2 2 1 0.25
## 6 2 3 1 0.25
## 7 2 5 2 0.5
## 8 3 3 1 0.167
## 9 3 5 4 0.667
## 10 3 7 1 0.167
## # ... with 17 more rowsData<-Data%>%
mutate(`Summary Scale` = ifelse(`Age`== "Normal", "Normal", "Non-normal"))#Summary statistics
Data%>%
group_by(`Group 1`, `InAverage`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'Group 1'. You can override using the
## `.groups` argument.## # A tibble: 26 x 4
## # Groups: Group 1 [3]
## `Group 1` InAverage count Percentage
## <chr> <dbl> <int> <dbl>
## 1 Less than 20 years old 5 1 0.0345
## 2 Less than 20 years old 8 1 0.0345
## 3 Less than 20 years old 11 3 0.103
## 4 Less than 20 years old 12 3 0.103
## 5 Less than 20 years old 14 2 0.0690
## 6 Less than 20 years old 15 7 0.241
## 7 Less than 20 years old 16 3 0.103
## 8 Less than 20 years old 17 1 0.0345
## 9 Less than 20 years old 18 2 0.0690
## 10 Less than 20 years old 19 6 0.207
## # ... with 16 more rows#### Summary statistics
Data%>%
group_by(`Group 2`, `InAverage`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'Group 2'. You can override using the
## `.groups` argument.## # A tibble: 35 x 4
## # Groups: Group 2 [2]
## `Group 2` InAverage count Percentage
## <chr> <dbl> <int> <dbl>
## 1 19 years old and below 12 1 0.0714
## 2 19 years old and below 18 1 0.0714
## 3 19 years old and below 19 1 0.0714
## 4 19 years old and below 22 2 0.143
## 5 19 years old and below 24 1 0.0714
## 6 19 years old and below 26 1 0.0714
## 7 19 years old and below 27 3 0.214
## 8 19 years old and below 28 2 0.143
## 9 19 years old and below 33 1 0.0714
## 10 19 years old and below 34 1 0.0714
## # ... with 25 more rows#### Summary statistics
Data%>%
group_by(`Group 1`, `Group 2`) %>%
summarise(count=n())%>%
mutate(Percentage =count/sum(count))## `summarise()` has grouped output by 'Group 1'. You can override using the
## `.groups` argument.## # A tibble: 5 x 4
## # Groups: Group 1 [3]
## `Group 1` `Group 2` count Percentage
## <chr> <chr> <int> <dbl>
## 1 Less than 20 years old 19 years old and below 3 0.103
## 2 Less than 20 years old at most 20 years old 26 0.897
## 3 More than 20 years old 19 years old and below 11 0.0866
## 4 More than 20 years old at most 20 years old 116 0.913
## 5 Normal at most 20 years old 7 1Data%>%
group_by(`Course Taken`)%>%
summarise(Frequency=n(), Mean = mean(InAverage), `Standard Deviation` = sd(InAverage))## # A tibble: 6 x 4
## `Course Taken` Frequency Mean `Standard Deviation`
## <chr> <int> <dbl> <dbl>
## 1 BS Biology 33 24.9 5.18
## 2 BS Civil Engineering 16 24.2 4.81
## 3 BS Electrical Engineering 17 24.2 3.86
## 4 BS Mathematics 33 23.7 5.85
## 5 BSED Biology 32 23.3 5.73
## 6 BSED English 32 23.7 6.57#Is there a significant difference between the two groups of age in terms of the variable “InAverage”?
two.way <- aov(InAverage ~ `Group 1` + `Group 2`, data = Data)
summary(two.way)## Df Sum Sq Mean Sq F value Pr(>F)
## `Group 1` 2 3196 1597.8 146.403 <2e-16 ***
## `Group 2` 1 15 14.8 1.359 0.245
## Residuals 159 1735 10.9
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1#Is there a significant difference among the courses taken in terms of the variable “InAverage”?
one.way <- aov(InAverage ~ `Course Taken`, data = Data)
summary(one.way)## Df Sum Sq Mean Sq F value Pr(>F)
## `Course Taken` 5 49 9.783 0.314 0.904
## Residuals 157 4897 31.189