9.9.2
Cúc
2024-09-09
ob = read.csv(“//Users//nguyenthicuc//Downloads//obesity data.csv”)
ob = read.csv("//Users//nguyenthicuc//Downloads//obesity data.csv")
dim(ob)## [1] 1217 13library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1(~ age + gender + bmi + WBBMC + wbbmd + fat + lean + hypertension + diabetes, data = ob)| Overall (N=1217) |
|
|---|---|
| age | |
| Mean (SD) | 47.2 (17.3) |
| Median [Min, Max] | 48.0 [13.0, 88.0] |
| gender | |
| F | 862 (70.8%) |
| M | 355 (29.2%) |
| bmi | |
| Mean (SD) | 22.4 (3.06) |
| Median [Min, Max] | 22.2 [14.5, 37.1] |
| WBBMC | |
| Mean (SD) | 1720 (363) |
| Median [Min, Max] | 1710 [695, 3040] |
| wbbmd | |
| Mean (SD) | 1.01 (0.113) |
| Median [Min, Max] | 1.01 [0.650, 1.35] |
| fat | |
| Mean (SD) | 17300 (5210) |
| Median [Min, Max] | 17000 [4280, 40800] |
| lean | |
| Mean (SD) | 35500 (7030) |
| Median [Min, Max] | 33600 [19100, 63100] |
| hypertension | |
| Mean (SD) | 0.507 (0.500) |
| Median [Min, Max] | 1.00 [0, 1.00] |
| diabetes | |
| Mean (SD) | 0.111 (0.314) |
| Median [Min, Max] | 0 [0, 1.00] |
table1(~ age + bmi + WBBMC + wbbmd + fat + lean + as.factor(hypertension) + as.factor(diabetes) | gender, data = ob)| F (N=862) |
M (N=355) |
Overall (N=1217) |
|
|---|---|---|---|
| age | |||
| Mean (SD) | 48.6 (16.4) | 43.7 (18.8) | 47.2 (17.3) |
| Median [Min, Max] | 49.0 [14.0, 85.0] | 44.0 [13.0, 88.0] | 48.0 [13.0, 88.0] |
| bmi | |||
| Mean (SD) | 22.3 (3.05) | 22.7 (3.04) | 22.4 (3.06) |
| Median [Min, Max] | 22.1 [15.2, 37.1] | 22.5 [14.5, 34.7] | 22.2 [14.5, 37.1] |
| WBBMC | |||
| Mean (SD) | 1600 (293) | 2030 (336) | 1720 (363) |
| Median [Min, Max] | 1610 [695, 2660] | 2030 [1190, 3040] | 1710 [695, 3040] |
| wbbmd | |||
| Mean (SD) | 0.988 (0.111) | 1.06 (0.101) | 1.01 (0.113) |
| Median [Min, Max] | 0.990 [0.650, 1.35] | 1.06 [0.780, 1.34] | 1.01 [0.650, 1.35] |
| fat | |||
| Mean (SD) | 18200 (4950) | 15000 (5110) | 17300 (5210) |
| Median [Min, Max] | 17700 [6220, 40800] | 15100 [4280, 29900] | 17000 [4280, 40800] |
| lean | |||
| Mean (SD) | 32000 (3970) | 43800 (5820) | 35500 (7030) |
| Median [Min, Max] | 31500 [19100, 53400] | 43400 [28600, 63100] | 33600 [19100, 63100] |
| as.factor(hypertension) | |||
| 0 | 430 (49.9%) | 170 (47.9%) | 600 (49.3%) |
| 1 | 432 (50.1%) | 185 (52.1%) | 617 (50.7%) |
| as.factor(diabetes) | |||
| 0 | 760 (88.2%) | 322 (90.7%) | 1082 (88.9%) |
| 1 | 102 (11.8%) | 33 (9.3%) | 135 (11.1%) |
library(compareGroups)
createTable(compareGroups(gender ~ age + bmi + WBBMC + wbbmd + fat + lean + hypertension + diabetes, data = ob))##
## --------Summary descriptives table by 'gender'---------
##
## ________________________________________________
## F M p.overall
## N=862 N=355
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## age 48.6 (16.4) 43.7 (18.8) <0.001
## bmi 22.3 (3.05) 22.7 (3.04) 0.013
## WBBMC 1599 (293) 2030 (336) <0.001
## wbbmd 0.99 (0.11) 1.06 (0.10) <0.001
## fat 18240 (4954) 14978 (5113) <0.001
## lean 32045 (3966) 43762 (5819) <0.001
## hypertension 0.50 (0.50) 0.52 (0.50) 0.527
## diabetes 0.12 (0.32) 0.09 (0.29) 0.181
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯ob$hypert = as.factor(ob$hypertension)
ob$dm = as.factor(ob$diabetes)
createTable(compareGroups(gender ~ age + bmi + WBBMC + wbbmd + fat + lean + hypert + dm, data = ob))##
## --------Summary descriptives table by 'gender'---------
##
## ___________________________________________
## F M p.overall
## N=862 N=355
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
## age 48.6 (16.4) 43.7 (18.8) <0.001
## bmi 22.3 (3.05) 22.7 (3.04) 0.013
## WBBMC 1599 (293) 2030 (336) <0.001
## wbbmd 0.99 (0.11) 1.06 (0.10) <0.001
## fat 18240 (4954) 14978 (5113) <0.001
## lean 32045 (3966) 43762 (5819) <0.001
## hypert: 0.569
## 0 430 (49.9%) 170 (47.9%)
## 1 432 (50.1%) 185 (52.1%)
## dm: 0.238
## 0 760 (88.2%) 322 (90.7%)
## 1 102 (11.8%) 33 (9.30%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯library(ggplot2)
library(gridExtra)
p = ggplot(data = ob, aes(x = pcfat))
p1 = p + geom_histogram()
p2 = p + geom_histogram(fill = "blue", col = "white") + labs(x = "Tỉ trọng mỡ (%)", y = "Số người", title = "Phân bố tỉ trọng mỡ")
grid.arrange(p1, p2, ncol = 2)## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.