t="/Users/locnguyen/Documents/R Console/Datasets for practice/Diabetes data.csv"
db=read.csv(t)
head(db)

##   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
## 4  1  43 Female    158     62    78  96   120    80      1            0
## 5  2  72 Female    148     47    91  95   130    60      1            0
## 6  2  44   Male    155     48    69  86   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
## 4 24.84 0.81   Normal
## 5 21.46 0.96      IFG
## 6 19.98 0.80   Normal

dung table1 tom tat du lieu theo gender

library(table1)

## 
## Attaching package: 'table1'

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

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

# dung table1 tom tat du lieu theo diabetes

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

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

# ty le mac benh tieu duong giua nam va nu #1. tao ra 1 bien moi chi co 2 gia tri Yes/No

db$diab = ifelse(db$diabetes=="Yes", "Yes", "No")
head(db)

##   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
## 4  1  43 Female    158     62    78  96   120    80      1            0
## 5  2  72 Female    148     47    91  95   130    60      1            0
## 6  2  44   Male    155     48    69  86   120    80      0            0
##     bmi  whr diabetes diab
## 1 19.95 0.97      IFG   No
## 2 22.97 0.79   Normal   No
## 3 24.12 0.91   Normal   No
## 4 24.84 0.81   Normal   No
## 5 21.46 0.96      IFG   No
## 6 19.98 0.80   Normal   No

tab= table(db$gender, db$diab)
tab

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

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

# kiem dinh Z ve khac biet giua 2 ti le tieu duong giua nam va nu (co ti le 0.01081...)-> ty le nam va nu khac nhau. (prop1 and prop2 la 2 gia tri khong bi tieu duong of gender)

cau 6 BMI giua nam va nu (tu ket qua nu thap hon nam hay nam hon nu)

phuong phap: phan tich phuong 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

phan tich nhom nu

tao ra mot data cho nu

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

#tao ra mot data cho nu

man= subset(db, gender=="Male")
dim(man)

## [1] 1004   15

ma=aov(bmi~diabetes, data=man)
TukeyHSD(ma)

##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = bmi ~ diabetes, data = man)
## 
## $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

#ve bieu do tuong quan da chieu cac bien lien tuc trong datasets

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 diab
## 1 19.95 0.97      IFG   No
## 2 22.97 0.79   Normal   No
## 3 24.12 0.91   Normal   No

# tao ra mot dataframe moi gom cac bien lien tuc (lien quan chat che va khong chat che -1< 0 >1)
dat = db[, c("age", "height", "weight", "bmi", "waist", "hip", "whr")]
library(psych)
pairs.panels(dat)