BaiThucHanh2
HATuan
2025-10-22
Bài 1
Việc 1: Đọc dữ liệu
ob=read.csv("D:\\DuLieu\\Tap huan\\Nam 2025\\Phuong phap NCKH\\Obesity data.csv")
head(ob)## id gender height weight bmi age WBBMC wbbmd fat lean pcfat hypertension
## 1 1 F 150 49 21.8 53 1312 0.88 17802 28600 37.3 0
## 2 2 M 165 52 19.1 65 1309 0.84 8381 40229 16.8 1
## 3 3 F 157 57 23.1 64 1230 0.84 19221 36057 34.0 1
## 4 4 F 156 53 21.8 56 1171 0.80 17472 33094 33.8 1
## 5 5 M 160 51 19.9 54 1681 0.98 7336 40621 14.8 0
## 6 6 F 153 47 20.1 52 1358 0.91 14904 30068 32.2 1
## diabetes
## 1 1
## 2 0
## 3 0
## 4 0
## 5 0
## 6 0Việc 2: Mô tả đặc điểm
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1( ~ age + gender + weight + height + pcfat + 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%) |
| weight | |
| Mean (SD) | 55.1 (9.40) |
| Median [Min, Max] | 54.0 [34.0, 95.0] |
| height | |
| Mean (SD) | 157 (7.98) |
| Median [Min, Max] | 155 [136, 185] |
| pcfat | |
| Mean (SD) | 31.6 (7.18) |
| Median [Min, Max] | 32.4 [9.20, 48.4] |
| 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] |
Việc 3: Tạo biến số định tính
ob$hyper=as.factor(ob$hypertension)
ob$dm=as.factor(ob$diabetes)
table1( ~ age + gender + weight + height + pcfat + hyper + dm, 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%) |
| weight | |
| Mean (SD) | 55.1 (9.40) |
| Median [Min, Max] | 54.0 [34.0, 95.0] |
| height | |
| Mean (SD) | 157 (7.98) |
| Median [Min, Max] | 155 [136, 185] |
| pcfat | |
| Mean (SD) | 31.6 (7.18) |
| Median [Min, Max] | 32.4 [9.20, 48.4] |
| hyper | |
| 0 | 600 (49.3%) |
| 1 | 617 (50.7%) |
| dm | |
| 0 | 1082 (88.9%) |
| 1 | 135 (11.1%) |
Việc 4:So sánh Nam và Nữ
library(compareGroups) createTable(compareGroups(gender ~ age + weight + height + pcfat + hyper + dm, data = ob)) ## Việc 5:Mô tả theo giới tính
table1(~ age + weight + height + pcfat + hyper + dm | 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] |
| weight | |||
| Mean (SD) | 52.3 (7.72) | 62.0 (9.59) | 55.1 (9.40) |
| Median [Min, Max] | 51.0 [34.0, 95.0] | 62.0 [38.0, 95.0] | 54.0 [34.0, 95.0] |
| height | |||
| Mean (SD) | 153 (5.55) | 165 (6.73) | 157 (7.98) |
| Median [Min, Max] | 153 [136, 170] | 165 [146, 185] | 155 [136, 185] |
| pcfat | |||
| Mean (SD) | 34.7 (5.19) | 24.2 (5.76) | 31.6 (7.18) |
| Median [Min, Max] | 34.7 [14.6, 48.4] | 24.6 [9.20, 39.0] | 32.4 [9.20, 48.4] |
| hyper | |||
| 0 | 430 (49.9%) | 170 (47.9%) | 600 (49.3%) |
| 1 | 432 (50.1%) | 185 (52.1%) | 617 (50.7%) |
| dm | |||
| 0 | 760 (88.2%) | 322 (90.7%) | 1082 (88.9%) |
| 1 | 102 (11.8%) | 33 (9.3%) | 135 (11.1%) |
Bài 2
Việc 1 : Dữ liệu tải trọng
A = c(14, 4, 10, 6, 3, 11, 12)
B = c(16, 17, 13, 12, 7, 16, 11, 8, 7)
wt = c(A, B)
group = c(rep("A", 7), rep("B", 9))
df = data.frame(wt, group)
dim(df)## [1] 16 2Việc 2: Đánh giá phân bố
library(lessR)##
## lessR 4.4.5 feedback: gerbing@pdx.edu
## --------------------------------------------------------------
## > d <- Read("") Read data file, many formats available, e.g., Excel
## d is default data frame, data= in analysis routines optional
##
## Many examples of reading, writing, and manipulating data,
## graphics, testing means and proportions, regression, factor analysis,
## customization, forecasting, and aggregation from pivot tables
## Enter: browseVignettes("lessR")
##
## View lessR updates, now including time series forecasting
## Enter: news(package="lessR")
##
## Interactive data analysis
## Enter: interact()##
## Attaching package: 'lessR'## The following object is masked from 'package:table1':
##
## labelHistogram(wt, data = df)## >>> Note: wt is not in a data frame (table)
## >>> Note: wt is not in a data frame (table)
## >>> Suggestions
## bin_width: set the width of each bin
## bin_start: set the start of the first bin
## bin_end: set the end of the last bin
## Histogram(wt, density=TRUE) # smoothed curve + histogram
## Plot(wt) # Violin/Box/Scatterplot (VBS) plot
##
## --- wt ---
##
## n miss mean sd min mdn max
## 16 0 10.44 4.29 3.00 11.00 17.00
##
##
## No (Box plot) outliers
##
##
## Bin Width: 2
## Number of Bins: 8
##
## Bin Midpnt Count Prop Cumul.c Cumul.p
## -------------------------------------------------
## 2 > 4 3 2 0.12 2 0.12
## 4 > 6 5 1 0.06 3 0.19
## 6 > 8 7 3 0.19 6 0.38
## 8 > 10 9 1 0.06 7 0.44
## 10 > 12 11 4 0.25 11 0.69
## 12 > 14 13 2 0.12 13 0.81
## 14 > 16 15 2 0.12 15 0.94
## 16 > 18 17 1 0.06 16 1.00
##