Midterm Exam
Justin Lian Caballero
2023-04-23
library(readxl)## Warning: package 'readxl' was built under R version 4.2.3library(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, unionlibrary(rstatix)## Warning: package 'rstatix' was built under R version 4.2.3##
## Attaching package: 'rstatix'## The following object is masked from 'package:stats':
##
## filterlibrary(tidyverse)## Warning: package 'tidyverse' was built under R version 4.2.3## Warning: package 'tidyr' was built under R version 4.2.3## Warning: package 'readr' was built under R version 4.2.3## Warning: package 'purrr' was built under R version 4.2.3## Warning: package 'forcats' was built under R version 4.2.3## Warning: package 'lubridate' was built under R version 4.2.3## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.4
## ✔ ggplot2 3.4.1 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.1.8
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ rstatix::filter() masks dplyr::filter(), stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errorslibrary(ggpubr)## Warning: package 'ggpubr' was built under R version 4.2.3library(readxl)
DATA<- read_excel("C:/StatMidterm 1to4/Dataques1to4.xlsx")
DATA## # A tibble: 158 × 38
## Responde…¹ School Age Sex Salar…² Marit…³ Year …⁴ Posit…⁵ Highe…⁶ `S-C 1`
## <dbl> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <dbl>
## 1 1 VCCS 30 Male 25,001… Married 2 T-I Colleg… 4
## 2 2 VCCS 38 Fema… 27,001… Married 2 T-II Colleg… 3
## 3 3 VCCS 40 Fema… 27,001… Married 2 T-II Colleg… 5
## 4 4 VCCS 40 Male 25,001… Married 4 T-I Colleg… 5
## 5 5 VCCS 54 Fema… 25,001… Married 2 T-I Colleg… 4
## 6 6 VCCS 41 Fema… 25,001… Married 2 T-I Colleg… 5
## 7 7 VCCS 40 Fema… 25,001… Married 3 T-I Colleg… 5
## 8 8 VCCS 63 Fema… 31,001… Married 3 T-III MAT 5
## 9 9 VCCS 53 Fema… 29,001… Married 1 T-III Colleg… 4
## 10 10 VCCS 46 Male 25,001… Married 6 T-I Colleg… 4
## # … with 148 more rows, 28 more variables: `S-C 2` <dbl>, `S-C 3` <dbl>,
## # `S-C 4` <dbl>, `S-C 5` <dbl>, SCTotal <dbl>, AveSC <dbl>, `FK 1` <dbl>,
## # `FK 2` <dbl>, `FK 3` <dbl>, `FK 4` <dbl>, `FK 5` <dbl>, FKTotal <dbl>,
## # AveFK <dbl>, `PI 1` <dbl>, `PI 2` <dbl>, `PI 3` <dbl>, `PI 4` <dbl>,
## # `PI 5` <dbl>, PITotal <dbl>, AvePI <dbl>, `RR 1` <dbl>, `RR 2` <dbl>,
## # `RR 3` <dbl>, `RR 4` <dbl>, `RR 5` <dbl>, Rrtotal <dbl>, AveRR <dbl>,
## # `Investment Alternatives` <chr>, and abbreviated variable names …Question # 1
Tatin1<- DATA%>%
filter(AveFK != "NA")%>%
mutate(AveFKFrequency= ifelse(AveFK <=1.49, "Very Poor",
ifelse(AveFK<=2.49, "Below Average",
ifelse(AveFK<=3.49, "Average",
ifelse(AveFK<=4.49, "Above Average","Excellent")))))%>%
group_by(School,AveFKFrequency)%>%
summarise(Frequency=n())%>%
mutate(Percentage =round(Frequency/sum(Frequency)*100, 2))## `summarise()` has grouped output by 'School'. You can override using the
## `.groups` argument.Tatin1## # A tibble: 7 × 4
## # Groups: School [2]
## School AveFKFrequency Frequency Percentage
## <chr> <chr> <int> <dbl>
## 1 VCCS Above Average 41 66.1
## 2 VCCS Average 7 11.3
## 3 VCCS Excellent 14 22.6
## 4 VNHS Above Average 68 70.8
## 5 VNHS Average 7 7.29
## 6 VNHS Below Average 2 2.08
## 7 VNHS Excellent 19 19.8Question # 2
Tatin2<- DATA%>%
filter(AveSC != "NA")%>%
mutate(AveSCFrequency= ifelse(AveSC <=1.49, "Very Poor",
ifelse(AveSC<=2.49, "Below Average",
ifelse(AveSC<=3.49, "Average",
ifelse(AveSC<=4.49, "Above Average","Excellent")))))%>%
group_by(School,AveSCFrequency)%>%
summarise(Frequency=n())%>%
mutate(Percentage =round(Frequency/sum(Frequency)*100, 2))## `summarise()` has grouped output by 'School'. You can override using the
## `.groups` argument.Tatin2## # A tibble: 8 × 4
## # Groups: School [2]
## School AveSCFrequency Frequency Percentage
## <chr> <chr> <int> <dbl>
## 1 VCCS Above Average 38 61.3
## 2 VCCS Average 14 22.6
## 3 VCCS Below Average 1 1.61
## 4 VCCS Excellent 9 14.5
## 5 VNHS Above Average 58 60.4
## 6 VNHS Average 24 25
## 7 VNHS Below Average 1 1.04
## 8 VNHS Excellent 13 13.5Question # 3
Tatin3<- DATA%>%
filter(AvePI != "NA")%>%
mutate(AvePIFrequency= ifelse(AvePI <=1.49, "Very Poor",
ifelse(AvePI<=2.49, "Below Average",
ifelse(AvePI<=3.49, "Average",
ifelse(AvePI<=4.49, "Above Average","Excellent")))))%>%
group_by(School,AvePIFrequency)%>%
summarise(Frequency=n())%>%
mutate(Percentage =round(Frequency/sum(Frequency)*100, 2))## `summarise()` has grouped output by 'School'. You can override using the
## `.groups` argument.Tatin3## # A tibble: 9 × 4
## # Groups: School [2]
## School AvePIFrequency Frequency Percentage
## <chr> <chr> <int> <dbl>
## 1 VCCS Above Average 39 62.9
## 2 VCCS Average 15 24.2
## 3 VCCS Below Average 1 1.61
## 4 VCCS Excellent 7 11.3
## 5 VNHS Above Average 49 51.0
## 6 VNHS Average 34 35.4
## 7 VNHS Below Average 7 7.29
## 8 VNHS Excellent 5 5.21
## 9 VNHS Very Poor 1 1.04Question # 4
Tatin4<- DATA%>%
filter(AveRR != "NA")%>%
mutate(AveRRFrequency= ifelse(AveRR <=1.49, "Very Poor",
ifelse(AveRR<=2.49, "Below Average",
ifelse(AveRR<=3.49, "Average",
ifelse(AveRR<=4.49, "Above Average","Excellent")))))%>%
group_by(School,AveRRFrequency)%>%
summarise(Frequency=n())%>%
mutate(Percentage =round(Frequency/sum(Frequency)*100, 2))## `summarise()` has grouped output by 'School'. You can override using the
## `.groups` argument.Tatin4## # A tibble: 7 × 4
## # Groups: School [2]
## School AveRRFrequency Frequency Percentage
## <chr> <chr> <int> <dbl>
## 1 VCCS Above Average 43 69.4
## 2 VCCS Average 11 17.7
## 3 VCCS Excellent 8 12.9
## 4 VNHS Above Average 67 69.8
## 5 VNHS Average 21 21.9
## 6 VNHS Below Average 3 3.12
## 7 VNHS Excellent 5 5.21library(ggplot2)
library(tibble)
library(tidyr)
library(readr)
library(purrr)
library(stringr)
library(forcats)library(readxl)
Jaswan<- read_excel("C:/StatMidterm 1to4/Dataquest5to11.xlsx")## New names:
## • `` -> `...6`
## • `` -> `...7`
## • `` -> `...8`
## • `` -> `...9`
## • `` -> `...10`
## • `` -> `...11`
## • `` -> `...12`library(rstatix)
Jaswan <- Jaswan%>%
gather(key ="Phase", value = "CFUcount", "Adlay with wash", "Adlay with milk and molasses", "Adlay with milk")%>%
convert_as_factor(Phase)
Jaswan## # A tibble: 192 × 11
## PhaseInterval Tempe…¹ ...6 ...7 ...8 ...9 ...10 ...11 ...12 Phase CFUco…²
## <chr> <chr> <lgl> <lgl> <chr> <chr> <chr> <chr> <chr> <fct> <dbl>
## 1 3- day 25°C NA NA <NA> <NA> <NA> <NA> <NA> Adla… 759
## 2 3- day 25°C NA NA Conc… dip Day Weig… Color Adla… 736
## 3 3- day 25°C NA NA 1 15 4 <NA> <NA> Adla… 891
## 4 3- day 30°C NA NA 1 15 4 <NA> <NA> Adla… 573
## 5 3- day 30°C NA NA 1 15 4 <NA> <NA> Adla… 584
## 6 3- day 30°C NA NA 1 15 4 <NA> <NA> Adla… 482
## 7 3- day 35°C NA NA 1 30 4 <NA> <NA> Adla… 384
## 8 3- day 35°C NA NA 1 30 4 <NA> <NA> Adla… 264
## 9 3- day 35°C NA NA 1 30 4 <NA> <NA> Adla… 208
## 10 5-day 25°C NA NA 1 30 4 <NA> <NA> Adla… 888
## # … with 182 more rows, and abbreviated variable names ¹Temperature, ²CFUcountQuestion # 5
#Summary statistics
Jaswan1<-Jaswan%>%
group_by(PhaseInterval) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Jaswan1## # A tibble: 3 × 5
## PhaseInterval variable n mean sd
## <chr> <fct> <dbl> <dbl> <dbl>
## 1 3- day CFUcount 26 488. 264.
## 2 5-day CFUcount 27 284. 269.
## 3 7-day CFUcount 27 182. 271.Question # 6
#Summary statistics
Jaswan2<-Jaswan%>%
group_by(Temperature) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Jaswan2## # A tibble: 3 × 5
## Temperature variable n mean sd
## <chr> <fct> <dbl> <dbl> <dbl>
## 1 25°C CFUcount 27 480. 353.
## 2 30°C CFUcount 26 235. 194.
## 3 35°C CFUcount 27 229. 243.Question # 7
#Summary statistics
Jaswan3<-Jaswan%>%
group_by(Phase) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Jaswan3## # A tibble: 3 × 5
## Phase variable n mean sd
## <fct> <fct> <dbl> <dbl> <dbl>
## 1 Adlay with milk CFUcount 26 190 232.
## 2 Adlay with milk and molasses CFUcount 27 293. 261.
## 3 Adlay with wash CFUcount 27 459. 323.Question # 8
#Summary statistics
Jaswan4<-Jaswan%>%
group_by(PhaseInterval, Temperature) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Jaswan4## # A tibble: 9 × 6
## PhaseInterval Temperature variable n mean sd
## <chr> <chr> <fct> <dbl> <dbl> <dbl>
## 1 3- day 25°C CFUcount 9 641. 244.
## 2 3- day 30°C CFUcount 8 347. 187.
## 3 3- day 35°C CFUcount 9 459. 282.
## 4 5-day 25°C CFUcount 9 460. 346.
## 5 5-day 30°C CFUcount 9 250. 218.
## 6 5-day 35°C CFUcount 9 142. 98.7
## 7 7-day 25°C CFUcount 9 340. 416.
## 8 7-day 30°C CFUcount 9 120. 108.
## 9 7-day 35°C CFUcount 9 85.4 104.Question # 9
#Summary statistics
Jaswan5<-Jaswan%>%
group_by(Temperature, Phase) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Jaswan5## # A tibble: 9 × 6
## Temperature Phase variable n mean sd
## <chr> <fct> <fct> <dbl> <dbl> <dbl>
## 1 25°C Adlay with milk CFUcount 9 243. 230.
## 2 25°C Adlay with milk and molasses CFUcount 9 416. 330.
## 3 25°C Adlay with wash CFUcount 9 783. 267.
## 4 30°C Adlay with milk CFUcount 8 84 57.6
## 5 30°C Adlay with milk and molasses CFUcount 9 193. 98.9
## 6 30°C Adlay with wash CFUcount 9 410. 213.
## 7 35°C Adlay with milk CFUcount 9 232. 309.
## 8 35°C Adlay with milk and molasses CFUcount 9 269. 271.
## 9 35°C Adlay with wash CFUcount 9 186. 135.Question # 10
library(readxl)
Justin<- read_excel("C:/StatMidterm 1to4/Dataques1to4.xlsx")ggplot(Justin, aes(x=School)) + geom_bar() + ggtitle('Respondents in Different School') + xlab('School')
ggplot(Justin, aes(x=Position)) + geom_bar() + ggtitle('Different Position of the Respondents') + xlab('Position') + theme_bw() + theme(axis.text.x = element_text(angle = 30, hjust = 1))