t="D:\\Datasets for practice\\Diabetes data.csv"
db=read.csv(t)
head(db,3)

##   id age gender height weight waist hip sysbp diabp active hypertension
## 1  1  76 Female    163     53    90  93   160    90      0            1
## 2  1  40 Female    149     51    74  94   100    60      0            0
## 3  1  51 Female    151     55    91 100   120    80      0            0
##     bmi  whr diabetes
## 1 19.95 0.97      IFG
## 2 22.97 0.79   Normal
## 3 24.12 0.91   Normal

library(table1)

## 
## Attaching package: 'table1'

## The following objects are masked from 'package:base':
## 
##     units, units<-

table1(~age+height+weight+waist+hip+whr+active+hypertension+diabetes|gender, data=db)

table1(~age+height+weight+waist+hip+whr+active+hypertension+diabetes|gender, data=db)

table1(~gender+age+height+weight++bmi+waist+hip+whr+active+hypertension|diabetes, data=db)

table1(~factor(gender)+age+height+weight++bmi+waist+hip+whr+factor(active)+factor(hypertension)|diabetes, data=db)

t.test(db$bmi~db$gender)

## 
##  Welch Two Sample t-test
## 
## data:  db$bmi by db$gender
## t = 0.66677, df = 2034.2, p-value = 0.505
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
##  -0.1749957  0.3552877
## sample estimates:
## mean in group Female   mean in group Male 
##             23.98515             23.89500

###. có sự khác biệt về tỷ lệ mắc bệnh tiểu đường giữa nam và nữ? # tạo biến mới có 2 giá trị yes,no

db$diab=ifelse(db$diabetes=="Yes","Yes","No")
tab=table(db$gender,db$diab)
tab

##         
##            No  Yes
##   Female 2014  147
##   Male    909   95

#Kiểm định z về sự khác biệt giữa hai tỉ lệ tiểu đường giữa nam và nữ

prop.test(tab)

## 
##  2-sample test for equality of proportions with continuity
##  correction
## 
## data:  tab
## X-squared = 6.496, df = 1, p-value = 0.01081
## alternative hypothesis: two.sided
## 95 percent confidence interval:
##  0.004880546 0.048314356
## sample estimates:
##    prop 1    prop 2 
## 0.9319759 0.9053785

# tính theo Chisq.test
chisq.test(tab)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  tab
## X-squared = 6.496, df = 1, p-value = 0.01081

#Kiểm định z về sự khác biệt giữa hai tỉ lệ tiểu đường giữa nam và nữ

prop.test(tab)

## 
##  2-sample test for equality of proportions with continuity
##  correction
## 
## data:  tab
## X-squared = 6.496, df = 1, p-value = 0.01081
## alternative hypothesis: two.sided
## 95 percent confidence interval:
##  0.004880546 0.048314356
## sample estimates:
##    prop 1    prop 2 
## 0.9319759 0.9053785

chisq.test(tab)

## 
##  Pearson's Chi-squared test with Yates' continuity correction
## 
## data:  tab
## X-squared = 6.496, df = 1, p-value = 0.01081

# phương pháp: phân tích phương sai(aov)
m=aov(bmi~diabetes, data=db)
summary(m)

##               Df Sum Sq Mean Sq F value  Pr(>F)   
## diabetes       2    151   75.27   5.851 0.00291 **
## Residuals   3153  40567   12.87                   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 9 observations deleted due to missingness

TukeyHSD(m)

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = bmi ~ diabetes, data = db)
## 
## $diabetes
##                  diff        lwr          upr     p adj
## Normal-IFG -0.8236127 -1.3882150 -0.259010503 0.0018313
## Yes-IFG    -0.7643882 -1.5297871  0.001010667 0.0503925
## Yes-Normal  0.0592245 -0.5064508  0.624899835 0.9673231

#phân tích cho nhóm nữ
# tạo ra một data cho nhóm nữ
women=subset(db,gender=="Female")
dim(women)

## [1] 2161   15

m=aov(bmi~diabetes,data = women)
TukeyHSD(m)

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = bmi ~ diabetes, data = women)
## 
## $diabetes
##                  diff       lwr       upr     p adj
## Normal-IFG -0.5165746 -1.228157 0.1950074 0.2044133
## Yes-IFG    -0.8256674 -1.808504 0.1571697 0.1198536
## Yes-Normal -0.3090928 -1.042806 0.4246202 0.5845178

# phân tích cho nam
men=subset(db,gender=="Male")
dim(men)

## [1] 1004   15

m=aov(bmi~diabetes,data = men)
TukeyHSD(m)

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = bmi ~ diabetes, data = men)
## 
## $diabetes
##                  diff        lwr        upr     p adj
## Normal-IFG -1.4155325 -2.3370305 -0.4940344 0.0009525
## Yes-IFG    -0.7331665 -1.9433880  0.4770551 0.3299207
## Yes-Normal  0.6823660 -0.1987307  1.5634627 0.1642512

dat=db[,c("age","weight","height","bmi","waist","hip","whr")]
library(psych)
pairs.panels(dat)

## Ý nghĩa: hệ số tương quan dao động từ 0-1 (0: ko có liên quan, 1: liên quan chặt chẽ).nếu hệ số tương quan âm=> thể hiện mối liên quan nghịch. ví dụ age & weight là tương quan nghịch(tuổi càng cao, chiều cao càng giảm)