This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
summary(cars)
## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00
You can also embed plots, for example:
library(table1)
##
## Attaching package: 'table1'
## The following objects are masked from 'package:base':
##
## units, units<-
library(magrittr)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x tidyr::extract() masks magrittr::extract()
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
## x purrr::set_names() masks magrittr::set_names()
library(compareGroups)
t<-"C:\\Users\\hntn\\OneDrive - Sun Hydraulics\\Hoa\\Ftu\\DATA ANALYSIS\\Dataset for TDTU workshop 4-2022\\Arrest dataset.csv"
arr<-read.csv(t)
head(arr)
## id age finance week arrest race work.exp married parole prior educ
## 1 1 27 no 20 1 black no not married yes 3 3
## 2 2 18 no 17 1 black no not married yes 8 4
## 3 3 19 no 25 1 other yes not married yes 13 3
## 4 4 23 yes 52 0 black yes married yes 1 5
## 5 5 19 no 52 0 other yes not married yes 3 3
## 6 6 24 no 52 0 black yes not married no 2 4
## employ1
## 1 no
## 2 no
## 3 no
## 4 no
## 5 no
## 6 no
dim(arr)
## [1] 432 12
arr$arrest1[arr$arrest==1]="Yes"
arr$arrest1[arr$arrest==0]="No"
head(arr)
## id age finance week arrest race work.exp married parole prior educ
## 1 1 27 no 20 1 black no not married yes 3 3
## 2 2 18 no 17 1 black no not married yes 8 4
## 3 3 19 no 25 1 other yes not married yes 13 3
## 4 4 23 yes 52 0 black yes married yes 1 5
## 5 5 19 no 52 0 other yes not married yes 3 3
## 6 6 24 no 52 0 black yes not married no 2 4
## employ1 arrest1
## 1 no Yes
## 2 no Yes
## 3 no Yes
## 4 no No
## 5 no No
## 6 no No
tail(arr)
## id age finance week arrest race work.exp married parole prior educ
## 427 427 22 yes 12 1 black yes married yes 2 4
## 428 428 31 yes 52 0 other yes not married yes 3 3
## 429 429 20 no 52 0 black no not married yes 1 4
## 430 430 20 yes 52 0 black yes married yes 1 3
## 431 431 29 no 52 0 black yes not married yes 3 4
## 432 432 24 yes 52 0 black yes not married yes 1 4
## employ1 arrest1
## 427 no Yes
## 428 no No
## 429 no No
## 430 no No
## 431 yes No
## 432 yes No
arr$fin[arr$finance=="yes"]=1
arr$fin[arr$finance=="no"]=0
head(arr)
## id age finance week arrest race work.exp married parole prior educ
## 1 1 27 no 20 1 black no not married yes 3 3
## 2 2 18 no 17 1 black no not married yes 8 4
## 3 3 19 no 25 1 other yes not married yes 13 3
## 4 4 23 yes 52 0 black yes married yes 1 5
## 5 5 19 no 52 0 other yes not married yes 3 3
## 6 6 24 no 52 0 black yes not married no 2 4
## employ1 arrest1 fin
## 1 no Yes 0
## 2 no Yes 0
## 3 no Yes 0
## 4 no No 1
## 5 no No 0
## 6 no No 0
summary(arr)
## id age finance week
## Min. : 1.0 Min. :17.0 Length:432 Min. : 1.00
## 1st Qu.:108.8 1st Qu.:20.0 Class :character 1st Qu.:50.00
## Median :216.5 Median :23.0 Mode :character Median :52.00
## Mean :216.5 Mean :24.6 Mean :45.85
## 3rd Qu.:324.2 3rd Qu.:27.0 3rd Qu.:52.00
## Max. :432.0 Max. :44.0 Max. :52.00
## arrest race work.exp married
## Min. :0.0000 Length:432 Length:432 Length:432
## 1st Qu.:0.0000 Class :character Class :character Class :character
## Median :0.0000 Mode :character Mode :character Mode :character
## Mean :0.2639
## 3rd Qu.:1.0000
## Max. :1.0000
## parole prior educ employ1
## Length:432 Min. : 0.000 Min. :2.000 Length:432
## Class :character 1st Qu.: 1.000 1st Qu.:3.000 Class :character
## Mode :character Median : 2.000 Median :3.000 Mode :character
## Mean : 2.984 Mean :3.477
## 3rd Qu.: 4.000 3rd Qu.:4.000
## Max. :18.000 Max. :6.000
## arrest1 fin
## Length:432 Length:432
## Class :character Class :character
## Mode :character Mode :character
##
##
##
#TOM TAT THONG KE DU LIEU QUA HAM TABLE 1 TRONG PACKAGE TABLE1
table1(~age+finance+fin+arrest+arrest1+race+parole+educ, data=arr)
| Overall (N=432) |
|
|---|---|
| age | |
| Mean (SD) | 24.6 (6.11) |
| Median [Min, Max] | 23.0 [17.0, 44.0] |
| finance | |
| no | 216 (50.0%) |
| yes | 216 (50.0%) |
| fin | |
| 0 | 216 (50.0%) |
| 1 | 216 (50.0%) |
| arrest | |
| Mean (SD) | 0.264 (0.441) |
| Median [Min, Max] | 0 [0, 1.00] |
| arrest1 | |
| No | 318 (73.6%) |
| Yes | 114 (26.4%) |
| race | |
| black | 379 (87.7%) |
| other | 53 (12.3%) |
| parole | |
| no | 165 (38.2%) |
| yes | 267 (61.8%) |
| educ | |
| Mean (SD) | 3.48 (0.834) |
| Median [Min, Max] | 3.00 [2.00, 6.00] |
#TOM TAT THONG KE THEO TINH TRANG HO TRO TAI CHINH (FINANCE)
table1(~age+finance+fin+arrest+arrest1+race+parole+educ|fin, data=arr)
| 0 (N=216) |
1 (N=216) |
Overall (N=432) |
|
|---|---|---|---|
| age | |||
| Mean (SD) | 24.2 (5.73) | 25.0 (6.47) | 24.6 (6.11) |
| Median [Min, Max] | 23.0 [17.0, 44.0] | 23.0 [17.0, 44.0] | 23.0 [17.0, 44.0] |
| finance | |||
| no | 216 (100%) | 0 (0%) | 216 (50.0%) |
| yes | 0 (0%) | 216 (100%) | 216 (50.0%) |
| fin | |||
| 0 | 216 (100%) | 0 (0%) | 216 (50.0%) |
| 1 | 0 (0%) | 216 (100%) | 216 (50.0%) |
| arrest | |||
| Mean (SD) | 0.306 (0.462) | 0.222 (0.417) | 0.264 (0.441) |
| Median [Min, Max] | 0 [0, 1.00] | 0 [0, 1.00] | 0 [0, 1.00] |
| arrest1 | |||
| No | 150 (69.4%) | 168 (77.8%) | 318 (73.6%) |
| Yes | 66 (30.6%) | 48 (22.2%) | 114 (26.4%) |
| race | |||
| black | 185 (85.6%) | 194 (89.8%) | 379 (87.7%) |
| other | 31 (14.4%) | 22 (10.2%) | 53 (12.3%) |
| parole | |||
| no | 81 (37.5%) | 84 (38.9%) | 165 (38.2%) |
| yes | 135 (62.5%) | 132 (61.1%) | 267 (61.8%) |
| educ | |||
| Mean (SD) | 3.44 (0.844) | 3.52 (0.824) | 3.48 (0.834) |
| Median [Min, Max] | 3.00 [2.00, 6.00] | 3.00 [2.00, 6.00] | 3.00 [2.00, 6.00] |
table1(~age+finance+fin+arrest+arrest1+race+parole+as.factor(educ)|fin, data=arr)
| 0 (N=216) |
1 (N=216) |
Overall (N=432) |
|
|---|---|---|---|
| age | |||
| Mean (SD) | 24.2 (5.73) | 25.0 (6.47) | 24.6 (6.11) |
| Median [Min, Max] | 23.0 [17.0, 44.0] | 23.0 [17.0, 44.0] | 23.0 [17.0, 44.0] |
| finance | |||
| no | 216 (100%) | 0 (0%) | 216 (50.0%) |
| yes | 0 (0%) | 216 (100%) | 216 (50.0%) |
| fin | |||
| 0 | 216 (100%) | 0 (0%) | 216 (50.0%) |
| 1 | 0 (0%) | 216 (100%) | 216 (50.0%) |
| arrest | |||
| Mean (SD) | 0.306 (0.462) | 0.222 (0.417) | 0.264 (0.441) |
| Median [Min, Max] | 0 [0, 1.00] | 0 [0, 1.00] | 0 [0, 1.00] |
| arrest1 | |||
| No | 150 (69.4%) | 168 (77.8%) | 318 (73.6%) |
| Yes | 66 (30.6%) | 48 (22.2%) | 114 (26.4%) |
| race | |||
| black | 185 (85.6%) | 194 (89.8%) | 379 (87.7%) |
| other | 31 (14.4%) | 22 (10.2%) | 53 (12.3%) |
| parole | |||
| no | 81 (37.5%) | 84 (38.9%) | 165 (38.2%) |
| yes | 135 (62.5%) | 132 (61.1%) | 267 (61.8%) |
| as.factor(educ) | |||
| 2 | 17 (7.9%) | 7 (3.2%) | 24 (5.6%) |
| 3 | 117 (54.2%) | 122 (56.5%) | 239 (55.3%) |
| 4 | 57 (26.4%) | 62 (28.7%) | 119 (27.5%) |
| 5 | 21 (9.7%) | 18 (8.3%) | 39 (9.0%) |
| 6 | 4 (1.9%) | 7 (3.2%) | 11 (2.5%) |
t=(compareGroups(finance~age+race+prior+parole,data=arr))
createTable(t)
##
## --------Summary descriptives table by 'finance'---------
##
## ___________________________________________
## no yes p.overall
## N=216 N=216
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## age 24.2 (5.73) 25.0 (6.47) 0.203
## race: 0.241
## black 185 (85.6%) 194 (89.8%)
## other 31 (14.4%) 22 (10.2%)
## prior 2.99 (2.92) 2.98 (2.88) 0.987
## parole: 0.843
## no 81 (37.5%) 84 (38.9%)
## yes 135 (62.5%) 132 (61.1%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
hist(arr$week)
ggplot(data=arr, aes(x=week))+geom_histogram(fill="violet", col="black")
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.