Bai tap ngay 2
Hien Ngo
2025-10-22
Bài tập ngày 2
Việc 1. Phân tích mô tả
1.1. Đọc dữ liệu vào R
ob = read.csv("E:\\Khoa XD\\Nam 2025-2026\\Tap huan 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 01.2. Mô tả đặc điểm
library(table1)##
## Attaching package: 'table1'## The following objects are masked from 'package:base':
##
## units, units<-table1(~age + gender + height + weight + 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%) |
| height | |
| Mean (SD) | 157 (7.98) |
| Median [Min, Max] | 155 [136, 185] |
| weight | |
| Mean (SD) | 55.1 (9.40) |
| Median [Min, Max] | 54.0 [34.0, 95.0] |
| 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] |
1.3. Nhận xét kết quả tiền căn bệnh cao huyết áp và tiểu đường
ob$hyper = as.factor(ob$hypertension)
ob$dm = as.factor(ob$diabetes)
table1(~age + gender + height + weight + pcfat + hypertension + hyper + diabetes + 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%) |
| height | |
| Mean (SD) | 157 (7.98) |
| Median [Min, Max] | 155 [136, 185] |
| weight | |
| Mean (SD) | 55.1 (9.40) |
| Median [Min, Max] | 54.0 [34.0, 95.0] |
| 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] |
| hyper | |
| 0 | 600 (49.3%) |
| 1 | 617 (50.7%) |
| diabetes | |
| Mean (SD) | 0.111 (0.314) |
| Median [Min, Max] | 0 [0, 1.00] |
| dm | |
| 0 | 1082 (88.9%) |
| 1 | 135 (11.1%) |
1.4. Trình bày Median (Q1, Q3)
table1(~ age + weight + height + pcfat, data = ob, render.continuous = c(. = "Mean (SD)", . = "Median [Q1, Q3]"))| Overall (N=1217) |
|
|---|---|
| age | |
| Mean (SD) | 47.2 (17.3) |
| Median [Q1, Q3] | 48.0 [35.0, 58.0] |
| weight | |
| Mean (SD) | 55.1 (9.40) |
| Median [Q1, Q3] | 54.0 [49.0, 61.0] |
| height | |
| Mean (SD) | 157 (7.98) |
| Median [Q1, Q3] | 155 [151, 162] |
| pcfat | |
| Mean (SD) | 31.6 (7.18) |
| Median [Q1, Q3] | 32.4 [27.0, 36.8] |
1.5. So sánh nam và nữ
table1(~age + height + weight + pcfat + hypertension + hyper + diabetes + 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] |
| height | |||
| Mean (SD) | 153 (5.55) | 165 (6.73) | 157 (7.98) |
| Median [Min, Max] | 153 [136, 170] | 165 [146, 185] | 155 [136, 185] |
| 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] |
| 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] |
| hypertension | |||
| Mean (SD) | 0.501 (0.500) | 0.521 (0.500) | 0.507 (0.500) |
| Median [Min, Max] | 1.00 [0, 1.00] | 1.00 [0, 1.00] | 1.00 [0, 1.00] |
| hyper | |||
| 0 | 430 (49.9%) | 170 (47.9%) | 600 (49.3%) |
| 1 | 432 (50.1%) | 185 (52.1%) | 617 (50.7%) |
| diabetes | |||
| Mean (SD) | 0.118 (0.323) | 0.0930 (0.291) | 0.111 (0.314) |
| Median [Min, Max] | 0 [0, 1.00] | 0 [0, 1.00] | 0 [0, 1.00] |
| dm | |||
| 0 | 760 (88.2%) | 322 (90.7%) | 1082 (88.9%) |
| 1 | 102 (11.8%) | 33 (9.3%) | 135 (11.1%) |
1.6. Đánh giá khác biệt giữa nam và nữ
library(compareGroups)
createTable(compareGroups(gender ~ age + height + weight + pcfat + hyper + 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
## height 153 (5.55) 165 (6.73) <0.001
## weight 52.3 (7.72) 62.0 (9.59) <0.001
## pcfat 34.7 (5.19) 24.2 (5.76) <0.001
## hyper: 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%)
## ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯Việc 2. Phân tích khác biệt giưa 2 nhóm
2.1. Nhập dữ liệu vào R
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 22.2. Tải trọng có tuân theo phân bố chuẩn
Dùng biểu đồ
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
## Dùng test
shapiro.test(df$wt)##
## Shapiro-Wilk normality test
##
## data: df$wt
## W = 0.96213, p-value = 0.70062.3. Mô tả đặc điểm về tải trọng của 2 nhóm
library(table1)
table1(~ wt | group, data = df, render.continuous = c(. = "Mean (SD)", . = "Median [Q1, Q3]"))| A (N=7) |
B (N=9) |
Overall (N=16) |
|
|---|---|---|---|
| wt | |||
| Mean (SD) | 8.57 (4.24) | 11.9 (3.95) | 10.4 (4.29) |
| Median [Q1, Q3] | 10.0 [5.00, 11.5] | 12.0 [8.00, 16.0] | 11.0 [7.00, 13.3] |
2.4. Thực hiện phép kiểm t để đánh giá khác biệt về tải trọng của 2 nhóm
t.test(A, B)##
## Welch Two Sample t-test
##
## data: A and B
## t = -1.6, df = 12.554, p-value = 0.1345
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -7.813114 1.178194
## sample estimates:
## mean of x mean of y
## 8.571429 11.888889t.test(wt ~ group, data = df)##
## Welch Two Sample t-test
##
## data: wt by group
## t = -1.6, df = 12.554, p-value = 0.1345
## alternative hypothesis: true difference in means between group A and group B is not equal to 0
## 95 percent confidence interval:
## -7.813114 1.178194
## sample estimates:
## mean in group A mean in group B
## 8.571429 11.8888892.5. Thực hiện bootstrap
library(simpleboot)## Simple Bootstrap Routines (1.1-8)library(boot)
b = two.boot(A, B, mean, R = 1000)
boot.ci(b)## BOOTSTRAP CONFIDENCE INTERVAL CALCULATIONS
## Based on 1000 bootstrap replicates
##
## CALL :
## boot.ci(boot.out = b)
##
## Intervals :
## Level Normal Basic
## 95% (-7.070, 0.543 ) (-7.205, 0.682 )
##
## Level Percentile BCa
## 95% (-7.317, 0.570 ) (-7.543, 0.362 )
## Calculations and Intervals on Original Scalehist(b, breaks = 50)
2.6. Sử dụng ChatGPT
# Dữ liệu
A <- c(14, 4, 10, 6, 3, 11, 12)
B <- c(16, 17, 13, 12, 7, 16, 11, 8, 7)
# Số lần lặp bootstrap
n_boot <- 10000
# Hàm tính chênh lệch trung bình
diff_means <- function(x, y) {
mean(x) - mean(y)
}
# Hàm bootstrap
set.seed(123) # để tái lập kết quả
boot_diff <- replicate(n_boot, {
sample_A <- sample(A, replace = TRUE)
sample_B <- sample(B, replace = TRUE)
diff_means(sample_A, sample_B)
})
# Kết quả thống kê
mean_diff <- mean(A) - mean(B)
ci <- quantile(boot_diff, c(0.025, 0.975)) # khoảng tin cậy 95%
p_value <- mean(boot_diff >= 0) # Xác suất hiệu trung bình >= 0 (tuỳ hướng giả thuyết)
cat("Chênh lệch trung bình gốc:", mean_diff, "\n")## Chênh lệch trung bình gốc: -3.31746cat("Khoảng tin cậy 95% (bootstrap):", ci, "\n")## Khoảng tin cậy 95% (bootstrap): -7.047619 0.4285714cat("Xác suất (hiệu trung bình >= 0):", p_value, "\n")## Xác suất (hiệu trung bình >= 0): 0.0441# Vẽ biểu đồ phân phối bootstrap
hist(boot_diff, breaks = 30, col = "lightblue", border = "white",
main = "Phân phối bootstrap của chênh lệch trung bình (A - B)",
xlab = "Hiệu trung bình")
abline(v = ci, col = "red", lwd = 2, lty = 2)
abline(v = mean_diff, col = "darkblue", lwd = 2)