bài 2 _ NHANES
Lanh Nguyen
2026-08-15
R Markdown
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. :120.00Including Plots
You can also embed plots, for example:
Note that the echo = FALSE parameter was added to the
code chunk to prevent printing of the R code that generated the
plot.
# Nạp gói NHANES
library(NHANES)
# Xem dữ liệu
data(NHANES)
# Số dòng và số cột
dim(NHANES)## [1] 10000 76# 10 dòng đầu tiên
head(NHANES, 10)## ID SurveyYr Gender Age AgeDecade AgeMonths Race1 Race3 Education
## 1 51624 2009_10 male 34 30-39 409 White <NA> High School
## 2 51624 2009_10 male 34 30-39 409 White <NA> High School
## 3 51624 2009_10 male 34 30-39 409 White <NA> High School
## 4 51625 2009_10 male 4 0-9 49 Other <NA> <NA>
## 5 51630 2009_10 female 49 40-49 596 White <NA> Some College
## 6 51638 2009_10 male 9 0-9 115 White <NA> <NA>
## 7 51646 2009_10 male 8 0-9 101 White <NA> <NA>
## 8 51647 2009_10 female 45 40-49 541 White <NA> College Grad
## 9 51647 2009_10 female 45 40-49 541 White <NA> College Grad
## 10 51647 2009_10 female 45 40-49 541 White <NA> College Grad
## MaritalStatus HHIncome HHIncomeMid Poverty HomeRooms HomeOwn Work
## 1 Married 25000-34999 30000 1.36 6 Own NotWorking
## 2 Married 25000-34999 30000 1.36 6 Own NotWorking
## 3 Married 25000-34999 30000 1.36 6 Own NotWorking
## 4 <NA> 20000-24999 22500 1.07 9 Own <NA>
## 5 LivePartner 35000-44999 40000 1.91 5 Rent NotWorking
## 6 <NA> 75000-99999 87500 1.84 6 Rent <NA>
## 7 <NA> 55000-64999 60000 2.33 7 Own <NA>
## 8 Married 75000-99999 87500 5.00 6 Own Working
## 9 Married 75000-99999 87500 5.00 6 Own Working
## 10 Married 75000-99999 87500 5.00 6 Own Working
## Weight Length HeadCirc Height BMI BMICatUnder20yrs BMI_WHO Pulse
## 1 87.4 NA NA 164.7 32.22 <NA> 30.0_plus 70
## 2 87.4 NA NA 164.7 32.22 <NA> 30.0_plus 70
## 3 87.4 NA NA 164.7 32.22 <NA> 30.0_plus 70
## 4 17.0 NA NA 105.4 15.30 <NA> 12.0_18.5 NA
## 5 86.7 NA NA 168.4 30.57 <NA> 30.0_plus 86
## 6 29.8 NA NA 133.1 16.82 <NA> 12.0_18.5 82
## 7 35.2 NA NA 130.6 20.64 <NA> 18.5_to_24.9 72
## 8 75.7 NA NA 166.7 27.24 <NA> 25.0_to_29.9 62
## 9 75.7 NA NA 166.7 27.24 <NA> 25.0_to_29.9 62
## 10 75.7 NA NA 166.7 27.24 <NA> 25.0_to_29.9 62
## BPSysAve BPDiaAve BPSys1 BPDia1 BPSys2 BPDia2 BPSys3 BPDia3 Testosterone
## 1 113 85 114 88 114 88 112 82 NA
## 2 113 85 114 88 114 88 112 82 NA
## 3 113 85 114 88 114 88 112 82 NA
## 4 NA NA NA NA NA NA NA NA NA
## 5 112 75 118 82 108 74 116 76 NA
## 6 86 47 84 50 84 50 88 44 NA
## 7 107 37 114 46 108 36 106 38 NA
## 8 118 64 106 62 118 68 118 60 NA
## 9 118 64 106 62 118 68 118 60 NA
## 10 118 64 106 62 118 68 118 60 NA
## DirectChol TotChol UrineVol1 UrineFlow1 UrineVol2 UrineFlow2 Diabetes
## 1 1.29 3.49 352 NA NA NA No
## 2 1.29 3.49 352 NA NA NA No
## 3 1.29 3.49 352 NA NA NA No
## 4 NA NA NA NA NA NA No
## 5 1.16 6.70 77 0.094 NA NA No
## 6 1.34 4.86 123 1.538 NA NA No
## 7 1.55 4.09 238 1.322 NA NA No
## 8 2.12 5.82 106 1.116 NA NA No
## 9 2.12 5.82 106 1.116 NA NA No
## 10 2.12 5.82 106 1.116 NA NA No
## DiabetesAge HealthGen DaysPhysHlthBad DaysMentHlthBad LittleInterest
## 1 NA Good 0 15 Most
## 2 NA Good 0 15 Most
## 3 NA Good 0 15 Most
## 4 NA <NA> NA NA <NA>
## 5 NA Good 0 10 Several
## 6 NA <NA> NA NA <NA>
## 7 NA <NA> NA NA <NA>
## 8 NA Vgood 0 3 None
## 9 NA Vgood 0 3 None
## 10 NA Vgood 0 3 None
## Depressed nPregnancies nBabies Age1stBaby SleepHrsNight SleepTrouble
## 1 Several NA NA NA 4 Yes
## 2 Several NA NA NA 4 Yes
## 3 Several NA NA NA 4 Yes
## 4 <NA> NA NA NA NA <NA>
## 5 Several 2 2 27 8 Yes
## 6 <NA> NA NA NA NA <NA>
## 7 <NA> NA NA NA NA <NA>
## 8 None 1 NA NA 8 No
## 9 None 1 NA NA 8 No
## 10 None 1 NA NA 8 No
## PhysActive PhysActiveDays TVHrsDay CompHrsDay TVHrsDayChild CompHrsDayChild
## 1 No NA <NA> <NA> NA NA
## 2 No NA <NA> <NA> NA NA
## 3 No NA <NA> <NA> NA NA
## 4 <NA> NA <NA> <NA> 4 1
## 5 No NA <NA> <NA> NA NA
## 6 <NA> NA <NA> <NA> 5 0
## 7 <NA> NA <NA> <NA> 1 6
## 8 Yes 5 <NA> <NA> NA NA
## 9 Yes 5 <NA> <NA> NA NA
## 10 Yes 5 <NA> <NA> NA NA
## Alcohol12PlusYr AlcoholDay AlcoholYear SmokeNow Smoke100 Smoke100n SmokeAge
## 1 Yes NA 0 No Yes Smoker 18
## 2 Yes NA 0 No Yes Smoker 18
## 3 Yes NA 0 No Yes Smoker 18
## 4 <NA> NA NA <NA> <NA> <NA> NA
## 5 Yes 2 20 Yes Yes Smoker 38
## 6 <NA> NA NA <NA> <NA> <NA> NA
## 7 <NA> NA NA <NA> <NA> <NA> NA
## 8 Yes 3 52 <NA> No Non-Smoker NA
## 9 Yes 3 52 <NA> No Non-Smoker NA
## 10 Yes 3 52 <NA> No Non-Smoker NA
## Marijuana AgeFirstMarij RegularMarij AgeRegMarij HardDrugs SexEver SexAge
## 1 Yes 17 No NA Yes Yes 16
## 2 Yes 17 No NA Yes Yes 16
## 3 Yes 17 No NA Yes Yes 16
## 4 <NA> NA <NA> NA <NA> <NA> NA
## 5 Yes 18 No NA Yes Yes 12
## 6 <NA> NA <NA> NA <NA> <NA> NA
## 7 <NA> NA <NA> NA <NA> <NA> NA
## 8 Yes 13 No NA No Yes 13
## 9 Yes 13 No NA No Yes 13
## 10 Yes 13 No NA No Yes 13
## SexNumPartnLife SexNumPartYear SameSex SexOrientation PregnantNow
## 1 8 1 No Heterosexual <NA>
## 2 8 1 No Heterosexual <NA>
## 3 8 1 No Heterosexual <NA>
## 4 NA NA <NA> <NA> <NA>
## 5 10 1 Yes Heterosexual <NA>
## 6 NA NA <NA> <NA> <NA>
## 7 NA NA <NA> <NA> <NA>
## 8 20 0 Yes Bisexual <NA>
## 9 20 0 Yes Bisexual <NA>
## 10 20 0 Yes Bisexual <NA>library(NHANES)
df <- NHANES[, c("Age", "Gender", "Race1", "Education",
"BMI", "BMI_WHO", "HHIncomeMid", "Poverty")]
# Kiểm tra
dim(df)## [1] 10000 8head(df, 10)## Age Gender Race1 Education BMI BMI_WHO HHIncomeMid Poverty
## 1 34 male White High School 32.22 30.0_plus 30000 1.36
## 2 34 male White High School 32.22 30.0_plus 30000 1.36
## 3 34 male White High School 32.22 30.0_plus 30000 1.36
## 4 4 male Other <NA> 15.30 12.0_18.5 22500 1.07
## 5 49 female White Some College 30.57 30.0_plus 40000 1.91
## 6 9 male White <NA> 16.82 12.0_18.5 87500 1.84
## 7 8 male White <NA> 20.64 18.5_to_24.9 60000 2.33
## 8 45 female White College Grad 27.24 25.0_to_29.9 87500 5.00
## 9 45 female White College Grad 27.24 25.0_to_29.9 87500 5.00
## 10 45 female White College Grad 27.24 25.0_to_29.9 87500 5.00names(df)## [1] "Age" "Gender" "Race1" "Education" "BMI"
## [6] "BMI_WHO" "HHIncomeMid" "Poverty"library(ggplot2)
# 1. Histogram thông thường
ggplot(df, aes(x = HHIncomeMid)) +
geom_histogram(bins = 30, fill = "steelblue", color = "white", alpha = 0.8) +
labs(
title = "Phân bố thu nhập hộ gia đình (HHIncomeMid)",
x = "Household Income Midpoint",
y = "Số lượng"
) +
theme_minimal(base_size = 13) +
theme(plot.title = element_text(hjust = 0.5, face = "bold"))## Warning: Removed 811 rows containing non-finite outside the scale range
## (`stat_bin()`).
library(ggplot2)
ggplot(df, aes(x = Education, fill = Education)) +
geom_bar(width = 0.7) +
geom_text(stat = "count", aes(label = after_stat(count)),
vjust = -0.4, size = 4) +
labs(
title = "Phân bố trình độ học vấn (Education)",
x = "Education",
y = "Frequency",
fill = "Education"
) +
theme_minimal(base_size = 13) +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
axis.text.x = element_text(angle = 30, hjust = 1),
legend.position = "none"
)
library(ggplot2)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union# Tính trung vị theo Education
df_median <- df %>%
group_by(Education) %>%
summarise(Median_Income = median(HHIncomeMid, na.rm = TRUE))
# Vẽ biểu đồ
ggplot(df_median, aes(x = Education, y = Median_Income, fill = Education)) +
geom_col(width = 0.7) +
geom_text(aes(label = round(Median_Income, 0)), vjust = -0.4, size = 4) +
labs(
title = "Trung vị thu nhập hộ gia đình theo trình độ học vấn",
x = "Education",
y = "Median of HHIncomeMid",
fill = "Education"
) +
theme_minimal(base_size = 13) +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
axis.text.x = element_text(angle = 30, hjust = 1),
legend.position = "none"
)
df_median_gender <- df %>%
group_by(Gender) %>%
summarise(Median_Income = median(HHIncomeMid, na.rm = TRUE))
ggplot(df_median_gender, aes(x = Gender, y = Median_Income, fill = Gender)) +
geom_col(width = 0.6) +
geom_text(aes(label = round(Median_Income, 0)), vjust = -0.4, size = 4.5) +
labs(
title = "Trung vị thu nhập hộ gia đình theo giới tính",
x = "Gender",
y = "Median of HHIncomeMid"
) +
theme_minimal(base_size = 13) +
theme(plot.title = element_text(hjust = 0.5, face = "bold"),
legend.position = "none")
library(ggplot2)
library(dplyr)
# Tính giá trị trung bình BMI theo Race1
df_bmi <- df %>%
group_by(Race1) %>%
summarise(Mean_BMI = mean(BMI, na.rm = TRUE))
# Vẽ biểu đồ
ggplot(df_bmi, aes(x = Race1, y = Mean_BMI, fill = Race1)) +
geom_col(width = 0.7) +
geom_text(aes(label = round(Mean_BMI, 1)), vjust = -0.4, size = 4) +
labs(
title = "Giá trị trung bình BMI theo chủng tộc (Race1)",
x = "Race1",
y = "Mean BMI",
fill = "Race1"
) +
theme_minimal(base_size = 13) +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
axis.text.x = element_text(angle = 30, hjust = 1),
legend.position = "none"
)
library(ggplot2)
ggplot(df, aes(x = Race1, y = HHIncomeMid, fill = Race1)) +
geom_boxplot(alpha = 0.8, outlier.shape = 21, outlier.size = 1.5) +
labs(
title = "Phân bố thu nhập hộ gia đình (HHIncomeMid) theo chủng tộc",
x = "Race1",
y = "HHIncomeMid",
fill = "Race1"
) +
theme_minimal(base_size = 13) +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
axis.text.x = element_text(angle = 30, hjust = 1),
legend.position = "none"
)## Warning: Removed 811 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
##8.3.6 Biểu đồ tương quan (scatterplot) giữa biến Age và BMI theo
Race1, có đường mô tả mối liên quan giữa Age và BMI theo phương pháp
loess (Locally Estimated Scatterplot Smoothing). Hãy tách thành biểu đồ
riêng cho từng Race1.##
library(ggplot2)
ggplot(df, aes(x = Age, y = BMI)) +
geom_point(alpha = 0.4, size = 1.2, color = "steelblue") +
geom_smooth(method = "loess", se = TRUE, color = "red", linewidth = 1) +
facet_wrap(~ Race1) +
labs(
title = "Mối liên quan giữa Age và BMI theo chủng tộc (Race1)",
x = "Age (years)",
y = "BMI",
caption = "Đường đỏ: Loess smoothing"
) +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
strip.text = element_text(face = "bold")
)## `geom_smooth()` using formula = 'y ~ x'## Warning: Removed 366 rows containing non-finite outside the scale range
## (`stat_smooth()`).## Warning: Removed 366 rows containing missing values or values outside the scale range
## (`geom_point()`).
library(ggplot2)
library(dplyr)
# Lọc bỏ giá trị thiếu
df_clean <- df %>%
filter(!is.na(Age) & !is.na(BMI) & !is.na(Race1))
# Vẽ biểu đồ
ggplot(df_clean, aes(x = Age, y = BMI)) +
geom_point(alpha = 0.4, size = 1.2, color = "steelblue") +
geom_smooth(method = "loess", se = TRUE, color = "red", linewidth = 1) +
facet_wrap(~ Race1) +
labs(
title = "Mối liên quan giữa Age và BMI theo chủng tộc (Race1)",
x = "Age (years)",
y = "BMI",
caption = "Đường đỏ: Loess smoothing"
) +
theme_minimal(base_size = 12) +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
strip.text = element_text(face = "bold")
)## `geom_smooth()` using formula = 'y ~ x'
ggplot(df_clean, aes(x = Age, y = BMI, color = Race1)) +
geom_point(alpha = 0.4, size = 1.2) +
geom_smooth(method = "loess", se = FALSE, linewidth = 1.1) +
labs(
title = "Mối liên quan giữa Age và BMI theo chủng tộc",
x = "Age (years)",
y = "BMI",
color = "Race1"
) +
theme_minimal(base_size = 13) +
theme(plot.title = element_text(hjust = 0.5, face = "bold"))## `geom_smooth()` using formula = 'y ~ x'