Data

library(readxl)
Data <- read_excel("D:/SIIT SHS STAT/Jay Ann/JAY ANN.xls")

New names:
• `Indicator 1` -> `Indicator 1...5`
• `Indicator 2` -> `Indicator 2...6`
• `Indicator 3` -> `Indicator 3...7`
• `Indicator 4` -> `Indicator 4...8`
• `Indicator 1` -> `Indicator 1...9`
• `Indicator 2` -> `Indicator 2...10`
• `Indicator 3` -> `Indicator 3...11`
• `Indicator 4` -> `Indicator 4...12`
• `Indicator 1` -> `Indicator 1...13`
• `Indicator 2` -> `Indicator 2...14`
• `Indicator 3` -> `Indicator 3...15`
• `Indicator 4` -> `Indicator 4...16`
• `Indicator 1` -> `Indicator 1...17`
• `Indicator 2` -> `Indicator 2...18`
• `Indicator 3` -> `Indicator 3...19`
• `Indicator 4` -> `Indicator 4...20`

View(Data)

library(rmarkdown)
paged_table(Data)

1. What is the demographic profile of the respondents in terms of:

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, union

Age

D1 <- Data%>%
  group_by(Age) %>%
  summarise(count=n())%>%
  mutate(Percentage =round((count/sum(count)*100),2))
paged_table(D1)

Sex

D2 <- Data%>%
  group_by(Sex) %>%
  summarise(count=n())%>%
  mutate(Percentage =round((count/sum(count)*100),2))
paged_table(D2)

Strand

D3 <- Data%>%
  group_by(`Strand`) %>%
  summarise(count=n())%>%
  mutate(Percentage =round((count/sum(count)*100),2))
paged_table(D3)

Normality Test

res_aov <- aov(`Financial` ~ Sex,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.972, p-value = 0.03151

Data is not normally distributed.

res_aov <- aov(`Socio Economic` ~ Sex,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.96136, p-value = 0.005036

Data is not normally distributed.

res_aov <- aov(`School Work` ~ Sex,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.94548, p-value = 0.000423

Data is not normally distributed.

res_aov <- aov(`Social Relation` ~ Sex,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.91761, p-value = 1.053e-05

Data is not normally distributed.

res_aov <- aov(`Financial` ~ Age,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.95886, p-value = 0.003339

Data is not normally distributed.

res_aov <- aov(`Socio Economic` ~ Age,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.95582, p-value = 0.002049

Data is not normally distributed.

res_aov <- aov(`School Work` ~ Age,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.94545, p-value = 0.0004212

Data is not normally distributed.

res_aov <- aov(`Social Relation` ~ Age,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.90954, p-value = 4.087e-06

Data is not normally distributed.

res_aov <- aov(`Financial` ~ Strand,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.97391, p-value = 0.04434

Data is not normally distributed.

res_aov <- aov(`Socio Economic` ~ Strand,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.96622, p-value = 0.01145

Data is not normally distributed.

res_aov <- aov(`School Work` ~ Strand,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.96949, p-value = 0.02019

Data is not normally distributed.

res_aov <- aov(`Social Relation` ~ Strand,
  data = Data
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.93104, p-value = 5.703e-05

Data is not normally distributed.

library(readxl)
library(dplyr)
library(car)

Loading required package: carData


Attaching package: 'car'

The following object is masked from 'package:dplyr':

    recode

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ forcats   1.0.0     ✔ readr     2.1.5
✔ ggplot2   3.4.4     ✔ stringr   1.5.1
✔ lubridate 1.9.3     ✔ tibble    3.2.1
✔ purrr     1.0.2     ✔ tidyr     1.3.1

── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
✖ car::recode()   masks dplyr::recode()
✖ purrr::some()   masks car::some()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(ggpubr)
library(rstatix)


Attaching package: 'rstatix'

The following object is masked from 'package:stats':

    filter

2nd SOP.

2.1. Sex

2.1.1 Financial and Sex

ggboxplot(Data, x = "Sex", y = "Financial",
          color = "Sex", palette = c("#00FF00", "#4E07FC"),
          order = c("Male", "Female"),
          ylab = "Financial", xlab = "Sex")

ggline(Data, x = "Sex", y = "Financial",
       add = c("mean_se", "jitter"),
       order = c("Male", "Female"),
       ylab = "Financial", xlab = "Sex")

library("gplots")


Attaching package: 'gplots'

The following object is masked from 'package:stats':

    lowess

plotmeans(`Financial` ~ Sex, data = Data, frame = TRUE,
          xlab = "Sex", ylab = "Financial",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Sex, order = c("Male", "Female"))

PlantGrowth %>%  
group_by(Sex) %>%
  get_summary_stats(`Financial`, type = "common")

# A tibble: 2 × 11
  Sex    variable      n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>     <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Male   Financial    35  2.25  3.75   3     0.25  3.11 0.35  0.059 0.12 
2 Female Financial    65  2     3.75   2.75  0.75  2.8  0.487 0.06  0.121

ggboxplot(PlantGrowth, x = "Sex", y = "Financial", fill="Sex")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Financial` ~ Sex)
res.kruskal

# A tibble: 1 × 6
  .y.           n statistic    df      p method        
* <chr>     <int>     <dbl> <int>  <dbl> <chr>         
1 Financial   100      10.3     1 0.0013 Kruskal-Wallis

Based on the p-value, there is significant difference between groups.

2.1.2 Socio-Economic and Sex

ggboxplot(Data, x = "Sex", y = "Socio Economic",
          color = "Sex", palette = c("#00FF00", "#4E07FC"),
          order = c("Male", "Female"),
          ylab = "Socio Economic", xlab = "Sex")

ggline(Data, x = "Sex", y = "Socio Economic",
       add = c("mean_se", "jitter"),
       order = c("Male", "Female"),
       ylab = "Socio Economic", xlab = "Sex")

library("gplots")
plotmeans(`Socio Economic` ~ Sex, data = Data, frame = TRUE,
          xlab = "Sex", ylab = "Socio Economic",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Sex, order = c("Male", "Female"))

PlantGrowth %>%  
group_by(Sex) %>%
  get_summary_stats(`Socio Economic`, type = "common")

# A tibble: 2 × 11
  Sex    variable           n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>          <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Male   Socio Economic    35  1.25   3.5   2.75  0.75  2.61 0.557 0.094 0.191
2 Female Socio Economic    65  1.5    3.5   2.75  0.75  2.66 0.485 0.06  0.12

ggboxplot(PlantGrowth, x = "Sex", y = "Socio Economic", fill="Sex")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Socio Economic` ~ Sex)
res.kruskal

# A tibble: 1 × 6
  .y.                n statistic    df     p method        
* <chr>          <int>     <dbl> <int> <dbl> <chr>         
1 Socio Economic   100   0.00772     1  0.93 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.1.3 School Work and Sex

ggboxplot(Data, x = "Sex", y = "School Work",
          color = "Sex", palette = c("#00FF00", "#4E07FC"),
          order = c("Male", "Female"),
          ylab = "School Work", xlab = "Sex")

ggline(Data, x = "Sex", y = "School Work",
       add = c("mean_se", "jitter"),
       order = c("Male", "Female"),
       ylab = "School Work", xlab = "Sex")

library("gplots")
plotmeans(`School Work` ~ Sex, data = Data, frame = TRUE,
          xlab = "Sex", ylab = "School Work",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Sex, order = c("Male", "Female"))

PlantGrowth %>%  
group_by(Sex) %>%
  get_summary_stats(`School Work`, type = "common")

# A tibble: 2 × 11
  Sex    variable        n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>       <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Male   School Work    35   2       4   3.25  0.5   3.15 0.425 0.072 0.146
2 Female School Work    65   2.5     4   3     0.25  3.14 0.342 0.042 0.085

ggboxplot(PlantGrowth, x = "Sex", y = "School Work", fill="Sex")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`School Work` ~ Sex)
res.kruskal

# A tibble: 1 × 6
  .y.             n statistic    df     p method        
* <chr>       <int>     <dbl> <int> <dbl> <chr>         
1 School Work   100     0.262     1 0.609 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.1.4 Social Relation and Sex

ggboxplot(Data, x = "Sex", y = "Social Relation",
          color = "Sex", palette = c("#00FF00", "#4E07FC"),
          order = c("Male", "Female"),
          ylab = "Social Relation", xlab = "Sex")

ggline(Data, x = "Sex", y = "Social Relation",
       add = c("mean_se", "jitter"),
       order = c("Male", "Female"),
       ylab = "Social Relation", xlab = "Sex")

library("gplots")
plotmeans(`Social Relation` ~ Sex, data = Data, frame = TRUE,
          xlab = "Sex", ylab = "Social Relation",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Sex, order = c("Male", "Female"))

PlantGrowth %>%  
group_by(Sex) %>%
  get_summary_stats(`Social Relation`, type = "common")

# A tibble: 2 × 11
  Sex    variable            n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>           <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Male   Social Relation    35  2.75     4    3.5  0.75  3.36 0.413 0.07  0.142
2 Female Social Relation    65  1.5      4    3.5  0.75  3.34 0.489 0.061 0.121

ggboxplot(PlantGrowth, x = "Sex", y = "Social Relation", fill="Sex")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Social Relation` ~ Sex)
res.kruskal

# A tibble: 1 × 6
  .y.                 n statistic    df     p method        
* <chr>           <int>     <dbl> <int> <dbl> <chr>         
1 Social Relation   100   0.00264     1 0.959 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.2. Age

2.2.1 Financial and Age

ggboxplot(Data, x = "Age", y = "Financial",
          color = "Age", palette = c("#00FF00", "#4E07FC"),
          order = c("17 - 18 years old", "19 years old and above"),
          ylab = "Financial", xlab = "Age")

ggline(Data, x = "Age", y = "Financial",
       add = c("mean_se", "jitter"),
       order = c("17 - 18 years old", "19 years old and above"),
       ylab = "Financial", xlab = "Age")

library("gplots")
plotmeans(`Financial` ~ Age, data = Data, frame = TRUE,
          xlab = "Age", ylab = "Financial",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Age, order = c("17 - 18 years old", "19 years old and above"))

PlantGrowth %>%  
group_by(Age) %>%
  get_summary_stats(`Financial`, type = "common")

# A tibble: 2 × 11
  Age            variable     n   min   max median   iqr  mean    sd    se    ci
  <fct>          <fct>    <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 17 - 18 years… Financi…    96  2     3.75   3    0.75   2.89 0.463 0.047 0.094
2 19 years old … Financi…     4  2.75  3.75   3.25 0.625  3.25 0.456 0.228 0.726

ggboxplot(PlantGrowth, x = "Age", y = "Financial", fill="Age")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Financial` ~ Age)
res.kruskal

# A tibble: 1 × 6
  .y.           n statistic    df     p method        
* <chr>     <int>     <dbl> <int> <dbl> <chr>         
1 Financial   100      1.95     1 0.162 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.2.2 Socio Economic and Age

ggboxplot(Data, x = "Age", y = "Socio Economic",
          color = "Age", palette = c("#00FF00", "#4E07FC"),
          order = c("17 - 18 years old", "19 years old and above"),
          ylab = "Socio Economic", xlab = "Age")

ggline(Data, x = "Age", y = "Socio Economic",
       add = c("mean_se", "jitter"),
       order = c("17 - 18 years old", "19 years old and above"),
       ylab = "Socio Economic", xlab = "Age")

library("gplots")
plotmeans(`Socio Economic` ~ Age, data = Data, frame = TRUE,
          xlab = "Age", ylab = "Socio Economic",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Age, order = c("17 - 18 years old", "19 years old and above"))

PlantGrowth %>%  
group_by(Age) %>%
  get_summary_stats(`Socio Economic`, type = "common")

# A tibble: 2 × 11
  Age            variable     n   min   max median   iqr  mean    sd    se    ci
  <fct>          <fct>    <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 17 - 18 years… Socio E…    96  1.25  3.5    2.75  0.75  2.64  0.51 0.052 0.103
2 19 years old … Socio E…     4  2     3.25   2.88  0.5   2.75  0.54 0.27  0.859

ggboxplot(PlantGrowth, x = "Age", y = "Socio Economic", fill="Age")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Socio Economic` ~ Age)
res.kruskal

# A tibble: 1 × 6
  .y.                n statistic    df     p method        
* <chr>          <int>     <dbl> <int> <dbl> <chr>         
1 Socio Economic   100     0.198     1 0.656 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.2.3 School Work and Age

ggboxplot(Data, x = "Age", y = "School Work",
          color = "Age", palette = c("#00FF00", "#4E07FC"),
          order = c("17 - 18 years old", "19 years old and above"),
          ylab = "School Work", xlab = "Age")

ggline(Data, x = "Age", y = "School Work",
       add = c("mean_se", "jitter"),
       order = c("17 - 18 years old", "19 years old and above"),
       ylab = "School Work", xlab = "Age")

library("gplots")
plotmeans(`School Work` ~ Age, data = Data, frame = TRUE,
          xlab = "Age", ylab = "School Work",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Age, order = c("17 - 18 years old", "19 years old and above"))

PlantGrowth %>%  
group_by(Age) %>%
  get_summary_stats(`School Work`, type = "common")

# A tibble: 2 × 11
  Age            variable     n   min   max median   iqr  mean    sd    se    ci
  <fct>          <fct>    <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 17 - 18 years… School …    96  2      4     3    0.312  3.14 0.373 0.038 0.076
2 19 years old … School …     4  2.75   3.5   3.25 0.562  3.19 0.375 0.188 0.597

ggboxplot(PlantGrowth, x = "Age", y = "School Work", fill="Age")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`School Work` ~ Age)
res.kruskal

# A tibble: 1 × 6
  .y.             n statistic    df     p method        
* <chr>       <int>     <dbl> <int> <dbl> <chr>         
1 School Work   100    0.0437     1 0.834 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.2.4 Social Relation and Age

ggboxplot(Data, x = "Age", y = "Social Relation",
          color = "Age", palette = c("#00FF00", "#4E07FC"),
          order = c("17 - 18 years old", "19 years old and above"),
          ylab = "Social Relation", xlab = "Age")

ggline(Data, x = "Age", y = "Social Relation",
       add = c("mean_se", "jitter"),
       order = c("17 - 18 years old", "19 years old and above"),
       ylab = "Social Relation", xlab = "Age")

library("gplots")
plotmeans(`Social Relation` ~ Age, data = Data, frame = TRUE,
          xlab = "Age", ylab = "Social Relation",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Age, order = c("17 - 18 years old", "19 years old and above"))

PlantGrowth %>%  
group_by(Age) %>%
  get_summary_stats(`Social Relation`, type = "common")

# A tibble: 2 × 11
  Age            variable     n   min   max median   iqr  mean    sd    se    ci
  <fct>          <fct>    <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 17 - 18 years… Social …    96   1.5   4     3.5  0.75   3.35 0.469 0.048 0.095
2 19 years old … Social …     4   3     3.5   3.38 0.312  3.31 0.239 0.12  0.381

ggboxplot(PlantGrowth, x = "Age", y = "Social Relation", fill="Age")

Wilcoxon Rank Sum Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Social Relation` ~ Age)
res.kruskal

# A tibble: 1 × 6
  .y.                 n statistic    df     p method        
* <chr>           <int>     <dbl> <int> <dbl> <chr>         
1 Social Relation   100     0.148     1 0.701 Kruskal-Wallis

Based on the p-value, there is no significant difference between groups.

2.3. Strand

2.3.1 Financial and Strand

ggboxplot(Data, x = "Strand", y = "Financial",
          color = "Strand", palette = c("#FC4E07", "#0000FF", "#00FF00", "#4E07FC"),
          order = c("STEM", "ABM", "HUMSS", "GAS"),
          ylab = "Financial", xlab = "Strand")

ggline(Data, x = "Strand", y = "Financial",
       add = c("mean_se", "jitter"),
       order = c("STEM", "ABM", "HUMSS", "GAS"),
       ylab = "Financial", xlab = "Strand")

library("gplots")
plotmeans(`Financial` ~ Strand, data = Data, frame = TRUE,
          xlab = "Strand", ylab = "Financial",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Strand, order = c("STEM", "ABM", "HUMSS", "GAS"))

PlantGrowth %>%  
group_by(Strand) %>%
  get_summary_stats(`Financial`, type = "common")

# A tibble: 4 × 11
  Strand variable      n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>     <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 STEM   Financial    19   2    3.75   2.75 0.75   2.68 0.513 0.118 0.247
2 ABM    Financial    22   2    3.75   2.75 0.688  2.89 0.468 0.1   0.207
3 HUMSS  Financial    23   2.5  3.75   3.25 0.5    3.13 0.36  0.075 0.156
4 GAS    Financial    36   2    3.75   2.88 0.75   2.90 0.453 0.075 0.153

ggboxplot(PlantGrowth, x = "Age", y = "Financial", fill="Age")

Kruskal-Wallis Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Financial` ~ Strand)
res.kruskal

# A tibble: 1 × 6
  .y.           n statistic    df      p method        
* <chr>     <int>     <dbl> <int>  <dbl> <chr>         
1 Financial   100      9.40     3 0.0244 Kruskal-Wallis

Based on the table above, there is significant difference between groups. ## Pairwise Comparisons

res1<- PlantGrowth %>%
  dunn_test(`Financial` ~ Strand, p.adjust.method = "bonferroni")
res1

# A tibble: 6 × 9
  .y.       group1 group2    n1    n2 statistic       p  p.adj p.adj.signif
* <chr>     <chr>  <chr>  <int> <int>     <dbl>   <dbl>  <dbl> <chr>       
1 Financial STEM   ABM       19    22     1.19  0.234   1      ns          
2 Financial STEM   HUMSS     19    23     3.01  0.00261 0.0157 *           
3 Financial STEM   GAS       19    36     1.45  0.147   0.883  ns          
4 Financial ABM    HUMSS     22    23     1.88  0.0600  0.360  ns          
5 Financial ABM    GAS       22    36     0.143 0.886   1      ns          
6 Financial HUMSS  GAS       23    36    -1.96  0.0505  0.303  ns

2.3.2 Socio Economic and Strand

ggboxplot(Data, x = "Strand", y = "Socio Economic",
          color = "Strand", palette = c("#FC4E07", "#0000FF", "#00FF00", "#4E07FC"),
          order = c("STEM", "ABM", "HUMSS", "GAS"),
          ylab = "Socio Economic", xlab = "Strand")

ggline(Data, x = "Strand", y = "Socio Economic",
       add = c("mean_se", "jitter"),
       order = c("STEM", "ABM", "HUMSS", "GAS"),
       ylab = "Socio Economic", xlab = "Strand")

library("gplots")
plotmeans(`Socio Economic` ~ Strand, data = Data, frame = TRUE,
          xlab = "Strand", ylab = "Socio Economic",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Strand, order = c("STEM", "ABM", "HUMSS", "GAS"))

PlantGrowth %>%  
group_by(Strand) %>%
  get_summary_stats(`Socio Economic`, type = "common")

# A tibble: 4 × 11
  Strand variable           n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>          <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 STEM   Socio Economic    19  2     3.25   2.75 0.625  2.66 0.435 0.1   0.21 
2 ABM    Socio Economic    22  1.5   3.5    2.62 0.75   2.64 0.581 0.124 0.258
3 HUMSS  Socio Economic    23  1.25  3.25   2.75 0.625  2.68 0.496 0.103 0.214
4 GAS    Socio Economic    36  1.5   3.5    2.5  0.75   2.62 0.526 0.088 0.178

ggboxplot(PlantGrowth, x = "Age", y = "Socio Economic", fill="Age")

Kruskal-Wallis Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Socio Economic` ~ Strand)
res.kruskal

# A tibble: 1 × 6
  .y.                n statistic    df     p method        
* <chr>          <int>     <dbl> <int> <dbl> <chr>         
1 Socio Economic   100     0.413     3 0.938 Kruskal-Wallis

Based on the table above, there is no significant difference between groups. ## Pairwise Comparisons

res1<- PlantGrowth %>%
  dunn_test(`Socio Economic` ~ Strand, p.adjust.method = "bonferroni")
res1

# A tibble: 6 × 9
  .y.            group1 group2    n1    n2 statistic     p p.adj p.adj.signif
* <chr>          <chr>  <chr>  <int> <int>     <dbl> <dbl> <dbl> <chr>       
1 Socio Economic STEM   ABM       19    22   -0.0944 0.925     1 ns          
2 Socio Economic STEM   HUMSS     19    23    0.405  0.686     1 ns          
3 Socio Economic STEM   GAS       19    36   -0.120  0.904     1 ns          
4 Socio Economic ABM    HUMSS     22    23    0.520  0.603     1 ns          
5 Socio Economic ABM    GAS       22    36   -0.0165 0.987     1 ns          
6 Socio Economic HUMSS  GAS       23    36   -0.598  0.550     1 ns

2.3.3 School Work and Strand

ggboxplot(Data, x = "Strand", y = "School Work",
          color = "Strand", palette = c("#FC4E07", "#0000FF", "#00FF00", "#4E07FC"),
          order = c("STEM", "ABM", "HUMSS", "GAS"),
          ylab = "School Work", xlab = "Strand")

ggline(Data, x = "Strand", y = "School Work",
       add = c("mean_se", "jitter"),
       order = c("STEM", "ABM", "HUMSS", "GAS"),
       ylab = "School Work", xlab = "Strand")

library("gplots")
plotmeans(`School Work` ~ Strand, data = Data, frame = TRUE,
          xlab = "Strand", ylab = "School Work",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Strand, order = c("STEM", "ABM", "HUMSS", "GAS"))

PlantGrowth %>%  
group_by(Strand) %>%
  get_summary_stats(`School Work`, type = "common")

# A tibble: 4 × 11
  Strand variable        n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>       <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 STEM   School Work    19   2.5  3.75   3    0.375  3.10 0.326 0.075 0.157
2 ABM    School Work    22   2.5  4      3    0      3.03 0.321 0.068 0.142
3 HUMSS  School Work    23   2.5  4      3.25 0.5    3.32 0.371 0.077 0.16 
4 GAS    School Work    36   2    3.75   3    0.5    3.12 0.399 0.066 0.135

ggboxplot(PlantGrowth, x = "Age", y = "School Work", fill="Age")

Kruskal-Wallis Test

res.kruskal <- PlantGrowth %>% kruskal_test(`School Work` ~ Strand)
res.kruskal

# A tibble: 1 × 6
  .y.             n statistic    df      p method        
* <chr>       <int>     <dbl> <int>  <dbl> <chr>         
1 School Work   100      9.11     3 0.0279 Kruskal-Wallis

Based on the table above, there is significant difference between groups. ## Pairwise Comparisons

res1<- PlantGrowth %>%
  dunn_test(`School Work` ~ Strand, p.adjust.method = "bonferroni")
res1

# A tibble: 6 × 9
  .y.         group1 group2    n1    n2 statistic       p  p.adj p.adj.signif
* <chr>       <chr>  <chr>  <int> <int>     <dbl>   <dbl>  <dbl> <chr>       
1 School Work STEM   ABM       19    22    -0.975 0.329   1      ns          
2 School Work STEM   HUMSS     19    23     1.87  0.0613  0.368  ns          
3 School Work STEM   GAS       19    36     0.370 0.711   1      ns          
4 School Work ABM    HUMSS     22    23     2.97  0.00298 0.0179 *           
5 School Work ABM    GAS       22    36     1.52  0.129   0.776  ns          
6 School Work HUMSS  GAS       23    36    -1.78  0.0751  0.451  ns

2.3.4 Social Relation and Strand

ggboxplot(Data, x = "Strand", y = "Social Relation",
          color = "Strand", palette = c("#FC4E07", "#0000FF", "#00FF00", "#4E07FC"),
          order = c("STEM", "ABM", "HUMSS", "GAS"),
          ylab = "Social Relation", xlab = "Strand")

ggline(Data, x = "Strand", y = "Social Relation",
       add = c("mean_se", "jitter"),
       order = c("STEM", "ABM", "HUMSS", "GAS"),
       ylab = "Social Relation", xlab = "Strand")

library("gplots")
plotmeans(`Social Relation` ~ Strand, data = Data, frame = TRUE,
          xlab = "Strand", ylab = "Social Relation",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data %>%
  reorder_levels(Strand, order = c("STEM", "ABM", "HUMSS", "GAS"))

PlantGrowth %>%  
group_by(Strand) %>%
  get_summary_stats(`Social Relation`, type = "common")

# A tibble: 4 × 11
  Strand variable            n   min   max median   iqr  mean    sd    se    ci
  <fct>  <fct>           <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 STEM   Social Relation    19  2.75     4   3.5  0.625  3.51 0.421 0.096 0.203
2 ABM    Social Relation    22  1.5      4   3.5  0.438  3.30 0.515 0.11  0.229
3 HUMSS  Social Relation    23  2.5      4   3.5  0.625  3.44 0.428 0.089 0.185
4 GAS    Social Relation    36  1.75     4   3.25 0.5    3.23 0.449 0.075 0.152

ggboxplot(PlantGrowth, x = "Age", y = "Social Relation", fill="Age")

Kruskal-Wallis Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Social Relation` ~ Strand)
res.kruskal

# A tibble: 1 × 6
  .y.                 n statistic    df      p method        
* <chr>           <int>     <dbl> <int>  <dbl> <chr>         
1 Social Relation   100      6.38     3 0.0946 Kruskal-Wallis

Based on the table above, there is no significant difference between groups. ## Pairwise Comparisons

res1<- PlantGrowth %>%
  dunn_test(`Social Relation` ~ Strand, p.adjust.method = "bonferroni")
res1

# A tibble: 6 × 9
  .y.             group1 group2    n1    n2 statistic      p p.adj p.adj.signif
* <chr>           <chr>  <chr>  <int> <int>     <dbl>  <dbl> <dbl> <chr>       
1 Social Relation STEM   ABM       19    22    -1.29  0.198  1     ns          
2 Social Relation STEM   HUMSS     19    23    -0.481 0.630  1     ns          
3 Social Relation STEM   GAS       19    36    -2.26  0.0237 0.142 ns          
4 Social Relation ABM    HUMSS     22    23     0.853 0.394  1     ns          
5 Social Relation ABM    GAS       22    36    -0.880 0.379  1     ns          
6 Social Relation HUMSS  GAS       23    36    -1.84  0.0651 0.390 ns

SOP Number 3

library(readxl)
Data1 <- read_excel("D:/SIIT SHS STAT/Jay Ann/Jay Ann.xlsx")
view(Data1)

res_aov <- aov(`Scores` ~ Variables,
  data = Data1
)
shapiro.test(res_aov$residuals)


    Shapiro-Wilk normality test

data:  res_aov$residuals
W = 0.97024, p-value = 2.8e-07

The data is not normally distributed.

Homogeneity of Variance

leveneTest(`Scores` ~ Variables,
  data = Data1)

Warning in leveneTest.default(y = y, group = group, ...): group coerced to
factor.

Levene's Test for Homogeneity of Variance (center = median)
       Df F value  Pr(>F)  
group   3  3.5038 0.01555 *
      396                  
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

ggboxplot(Data1, x = "Variables", y = "Scores",
          color = "Variables", palette = c("#FC4E07", "#0000FF", "#00FF00", "#4E07FC"),
          order = c("Financial", "Socio Economic", "School Work", "Social Relation"),
          ylab = "Scores", xlab = "Variables")

ggline(Data1, x = "Variables", y = "Scores",
       add = c("mean_se", "jitter"),
       order = c("Financial", "Socio Economic", "School Work", "Social Relation"),
       ylab = "Scores", xlab = "Variables")

library("gplots")
plotmeans(`Scores` ~ Variables, data = Data1, frame = FALSE,
          xlab = "Variables", ylab = "Scores",
          main="Mean Plot with 95% CI")

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

Warning in axis(1, at = 1:length(means), labels = legends, ...): "frame" is not
a graphical parameter

Warning in plot.xy(xy.coords(x, y), type = type, ...): "frame" is not a
graphical parameter

PlantGrowth <- Data1 %>%
  reorder_levels(Variables, order = c("Financial", "Socio Economic", "School Work", "Social Relation"))

PlantGrowth %>%  
group_by(Variables) %>%
  get_summary_stats(`Scores`, type = "common")

# A tibble: 4 × 11
  Variables      variable     n   min   max median   iqr  mean    sd    se    ci
  <fct>          <fct>    <dbl> <dbl> <dbl>  <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Financial      Scores     100  2     3.75   3     0.75  2.91 0.466 0.047 0.092
2 Socio Economic Scores     100  1.25  3.5    2.75  0.75  2.64 0.509 0.051 0.101
3 School Work    Scores     100  2     4      3     0.5   3.14 0.371 0.037 0.074
4 Social Relati… Scores     100  1.5   4      3.5   0.75  3.34 0.462 0.046 0.092

The mean of teaching method, teaching quality, and students engagement is 3.002, 3.046, and 3.094, respectively.

ggboxplot(PlantGrowth, x = "Variables", y = "Scores", fill="Variables")

Kruskal-wallis Test

res.kruskal <- PlantGrowth %>% kruskal_test(`Scores` ~ Variables)
res.kruskal

# A tibble: 1 × 6
  .y.        n statistic    df        p method        
* <chr>  <int>     <dbl> <int>    <dbl> <chr>         
1 Scores   400      100.     3 1.43e-21 Kruskal-Wallis

Based on the p-value, there is significant difference was observed between the group pairs.

Pairwise Comparisons

res1<- PlantGrowth %>%
  dunn_test(`Scores` ~ Variables, p.adjust.method = "bonferroni")
res1

# A tibble: 6 × 9
  .y.    group1      group2    n1    n2 statistic        p    p.adj p.adj.signif
* <chr>  <chr>       <chr>  <int> <int>     <dbl>    <dbl>    <dbl> <chr>       
1 Scores Financial   Socio…   100   100     -3.10 1.91e- 3 1.15e- 2 *           
2 Scores Financial   Schoo…   100   100      3.22 1.29e- 3 7.76e- 3 **          
3 Scores Financial   Socia…   100   100      6.37 1.84e-10 1.11e- 9 ****        
4 Scores Socio Econ… Schoo…   100   100      6.32 2.61e-10 1.56e- 9 ****        
5 Scores Socio Econ… Socia…   100   100      9.48 2.62e-21 1.57e-20 ****        
6 Scores School Work Socia…   100   100      3.16 1.60e- 3 9.58e- 3 **

Pairwise, there is significant difference.

4. Which have the most significant impact?

Based on the provided output above, it can be seen that it is the social relation.

Jay Ann Group Statistical Analysis

Kyle Kenneth Ruaya

2024-05-05

Data

1. What is the demographic profile of the respondents in terms of:

Age

Sex

Strand

Normality Test

2nd SOP.

2.1. Sex

2.1.1 Financial and Sex

Wilcoxon Rank Sum Test

2.1.2 Socio-Economic and Sex

Wilcoxon Rank Sum Test

2.1.3 School Work and Sex

Wilcoxon Rank Sum Test

Wilcoxon Rank Sum Test

2.2. Age

2.2.1 Financial and Age

Wilcoxon Rank Sum Test

2.2.2 Socio Economic and Age

Wilcoxon Rank Sum Test

2.2.3 School Work and Age

Wilcoxon Rank Sum Test

Wilcoxon Rank Sum Test

2.3. Strand

2.3.1 Financial and Strand

Kruskal-Wallis Test

2.3.2 Socio Economic and Strand

Kruskal-Wallis Test

2.3.3 School Work and Strand

Kruskal-Wallis Test

Kruskal-Wallis Test

SOP Number 3

Homogeneity of Variance

Kruskal-wallis Test

Pairwise Comparisons

4. Which have the most significant impact?