STAT50 MIDTERM EXAM
VANESSA LARAZO BANA
2023-03-23
library(readxl)
Luna <- read_excel("E:/STAT50/MTE/Alliah1.xlsx")
Luna## # 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
library(dplyr)
Luna %>%
mutate(AveFKFrequency = recode(AveFK, "2.0"="Below Average", "2.6"="Average", "2.8"="Average", "3.0"="Average", "3.2"="Average", "3.4"="Average", "3.6"="Above Average", "3.8"="Above Average", "4.0"="Above Average", "4.2"="Above Average", "4.4"="Above Average","4.6"="Excellent", "4.8"="Excellent", "5.0"="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.## # 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 19.8*Question 2
library(dplyr)
Luna %>%
mutate(AveSCFrequency = recode(AveSC, "2.4"="Below Average", "2.6"="Average", "2.8"="Average", "3.0"="Average", "3.2"="Average", "3.4"="Average", "3.6"="Above Average", "3.8"="Above Average", "4.0"="Above Average", "4.2"="Above Average", "4.4"="Above Average", "4.6"="Excellent", "4.8"="Excellent", "5.0"="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.## # 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 13.5*Question 3
library(dplyr)
Luna %>%
mutate(AvePIFrequency = recode(AvePI, "1.6"=" Below Average", "2.2"="Below Average", "2.4"="Below Average", "2.6"="Average", "2.8"="Average", "3.0"="Average", "3.2"="Average", "3.4"="Average", "3.6"="Above Average", "3.8"="Above Average", "4.0"="Above Average", "4.2"="Above Average", "4.4"="Above Average", "4.6"="Excellent", "4.8"="Excellent", "5.0"="Excellent", "2.0"=" Below Average", "0.0"="Very Poor")) %>%
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.## # A tibble: 10 × 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 " Below Average" 3 3.12
## 6 VNHS "Above Average" 49 51.0
## 7 VNHS "Average" 34 35.4
## 8 VNHS "Below Average" 4 4.17
## 9 VNHS "Excellent" 5 5.21
## 10 VNHS "Very Poor" 1 1.04*Question 4
library(dplyr)
Luna %>%
mutate(AveRRFrequency = recode (AveRR, "2.0"="Below Average", "2.4"="Below Average", "2.6"="Below Average", "2.8"="Average", "3.0"="Average", "3.2"="Average", "3.4"="Average", "3.6"="Above Average", "3.8"="Above Average", "4.0"="Above Average", "4.2"="Above Average", "4.4"="Above Average", "4.6"="Excellent", "4.8"="Excellent", "5.0"="Excellent")) %>%
group_by(School, AveRRFrequency) %>%
summarise(Frequency=n()) %>%
mutate(Percentage = round(Frequency/sum(Frequency)*100))## `summarise()` has grouped output by 'School'. You can override using the
## `.groups` argument.## # A tibble: 8 × 4
## # Groups: School [2]
## School AveRRFrequency Frequency Percentage
## <chr> <chr> <int> <dbl>
## 1 VCCS Above Average 43 69
## 2 VCCS Average 10 16
## 3 VCCS Below Average 1 2
## 4 VCCS Excellent 8 13
## 5 VNHS Above Average 67 70
## 6 VNHS Average 19 20
## 7 VNHS Below Average 5 5
## 8 VNHS Excellent 5 5library(readxl)
Kyro <- read_excel("E:/STAT50/MTE/Alliah2.xlsx")## New names:
## • `` -> `...6`
## • `` -> `...7`
## • `` -> `...8`
## • `` -> `...9`
## • `` -> `...10`
## • `` -> `...11`
## • `` -> `...12`Kyro## # A tibble: 64 × 12
## PhaseIn…¹ Tempe…² Adlay…³ Adlay…⁴ Adlay…⁵ ...6 ...7 ...8 ...9 ...10 ...11
## <chr> <chr> <dbl> <dbl> <dbl> <lgl> <lgl> <chr> <chr> <chr> <chr>
## 1 3- day 25°C 759 220 819 NA NA <NA> <NA> <NA> <NA>
## 2 3- day 25°C 736 812 763 NA NA Conc… dip Day Weig…
## 3 3- day 25°C 891 316 457 NA NA 1 15 4 <NA>
## 4 3- day 30°C 573 96 356 NA NA 1 15 4 <NA>
## 5 3- day 30°C 584 137 247 NA NA 1 15 4 <NA>
## 6 3- day 30°C 482 NA 298 NA NA 1 15 4 <NA>
## 7 3- day 35°C 384 79 346 NA NA 1 30 4 <NA>
## 8 3- day 35°C 264 934 823 NA NA 1 30 4 <NA>
## 9 3- day 35°C 208 556 536 NA NA 1 30 4 <NA>
## 10 5-day 25°C 888 267 879 NA NA 1 30 4 <NA>
## # … with 54 more rows, 1 more variable: ...12 <chr>, and abbreviated variable
## # names ¹PhaseInterval, ²Temperature, ³`Adlay with wash`, ⁴`Adlay with milk`,
## # ⁵`Adlay with milk and molasses`library(rstatix)
Phase <- Kyro %>%
gather(key ="Phase", value = "CFUcount", 'Adlay with wash', 'Adlay with milk', 'Adlay with milk and molasses') %>%
convert_as_factor(Phase)
Phase## # 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, ²CFUcount*Question 5
Sky <- Phase %>%
group_by(PhaseInterval) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Sky## # 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
Rain <- Phase %>%
group_by(Temperature) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Rain## # 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
Cloud <- Phase %>%
group_by(Phase) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Cloud## # 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
Thunder <- Phase %>%
group_by(Temperature, PhaseInterval) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Thunder## # 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 5-day 25°C CFUcount 9 460. 346.
## 3 7-day 25°C CFUcount 9 340. 416.
## 4 3- day 30°C CFUcount 8 347. 187.
## 5 5-day 30°C CFUcount 9 250. 218.
## 6 7-day 30°C CFUcount 9 120. 108.
## 7 3- day 35°C CFUcount 9 459. 282.
## 8 5-day 35°C CFUcount 9 142. 98.7
## 9 7-day 35°C CFUcount 9 85.4 104.*Question 9
Fogs <- Phase %>%
group_by(Temperature,Phase) %>%
get_summary_stats(CFUcount, type = "mean_sd")
Fogs## # 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
Data 5
hist(Sky$n, col="blue")
hist(Sky$mean, col="red")
hist(Sky$sd, col="green")
Data 7
with(Cloud, plot(mean, sd))