Đọc dữ liệu

t = "C:\\Users\\SONY\\Google Drive\\HOC TAP\\CH 22\\Phan tich du lieu\\Workshop GS Tuan\\Phan tich du lieu va ung dung\\Datasets for practice\\Hip fracture data.csv"
dat = read.csv(t, na.strings = "")

Chon doi tuong co v2 < 2 dua vao dataframe "hh:

Chon bien lien quan trong dat1

hip = dat1[,c("hipfx", "gender", "age", "v2", "v3", "bmi", "v4", "v5")]

#imputation

library(mice)

## Loading required package: lattice

## 
## Attaching package: 'mice'

## The following objects are masked from 'package:base':
## 
##     cbind, rbind

library(VIM)

## Loading required package: colorspace

## Loading required package: grid

## Loading required package: data.table

## VIM is ready to use. 
##  Since version 4.0.0 the GUI is in its own package VIMGUI.
## 
##           Please use the package to use the new (and old) GUI.

## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues

## 
## Attaching package: 'VIM'

## The following object is masked from 'package:datasets':
## 
##     sleep

Xem pattern of missing data

md.pattern(hip)

##      hipfx gender age v2 v3 bmi v4  v5    
## 2328     1      1   1  1  1   1  1   1   0
## 355      1      1   1  1  1   1  1   0   1
## 29       1      1   1  1  1   1  0   1   1
## 3        1      1   1  1  1   1  0   0   2
## 3        1      1   1  1  1   0  1   1   1
## 4        1      1   1  1  1   0  1   0   2
##          0      0   0  0  0   7 32 362 401

# impute dữ liệu bằng phương pháp MICE
ms.hip= mice(hip, seed=1234, printFlag=F)

Hoàn thiện data

ihip = complete(ms.hip)

Kiểm ta dataset sau imputation

head(ihip)

##   hipfx gender age   v2    v3 bmi    v4 v5
## 1     0   Male  73 0.88 1.079  32 1.458 44
## 2     0 Female  67 0.85 0.966  26 1.325 18
## 3     0   Male  68 0.84 1.013  26 1.494 36
## 4     0 Female  62 0.71 0.839  24 1.214 25
## 5     0   Male  61 0.60 0.811  24 1.144 44
## 6     0 Female  76 0.58 0.743  28 0.980 15