| Missing Values |
title: “Mice” author: “William” date: ‘2022-03-16’ output: html_document —
#installing mice
#install.packages("mice")
library("mice")## Warning: package 'mice' was built under R version 4.1.3##
## Attaching package: 'mice'## The following object is masked from 'package:stats':
##
## filter## The following objects are masked from 'package:base':
##
## cbind, rbind?mice## starting httpd help server ...## done#using inbuilt dataset
data1<-nhanes
head(data1)## age bmi hyp chl
## 1 1 NA NA NA
## 2 2 22.7 1 187
## 3 1 NA 1 187
## 4 3 NA NA NA
## 5 1 20.4 1 113
## 6 3 NA NA 184Mice comes in handy when imputing categorical records
#checking the summary
summary(data1)## age bmi hyp chl
## Min. :1.00 Min. :20.40 Min. :1.000 Min. :113.0
## 1st Qu.:1.00 1st Qu.:22.65 1st Qu.:1.000 1st Qu.:185.0
## Median :2.00 Median :26.75 Median :1.000 Median :187.0
## Mean :1.76 Mean :26.56 Mean :1.235 Mean :191.4
## 3rd Qu.:2.00 3rd Qu.:28.93 3rd Qu.:1.000 3rd Qu.:212.0
## Max. :3.00 Max. :35.30 Max. :2.000 Max. :284.0
## NA's :9 NA's :8 NA's :10Observation: you can’t check the min, median, or mean of binary values i.e hyp. therefore we need to change the variable to the right datatype
#convert hype to a factor
data1$hyp=as.factor(data1$hyp)
#confirming the canges
is.factor(data1$hyp)## [1] TRUE#checking the summary
summary(data1)## age bmi hyp chl
## Min. :1.00 Min. :20.40 1 :13 Min. :113.0
## 1st Qu.:1.00 1st Qu.:22.65 2 : 4 1st Qu.:185.0
## Median :2.00 Median :26.75 NA's: 8 Median :187.0
## Mean :1.76 Mean :26.56 Mean :191.4
## 3rd Qu.:2.00 3rd Qu.:28.93 3rd Qu.:212.0
## Max. :3.00 Max. :35.30 Max. :284.0
## NA's :9 NA's :10#Replacing bmi and chl NA with the mean since they are continous varaibles
data1$bmi[which(is.na(data1$bmi))]=mean(data1$bmi,na.rm = TRUE)
data1$chl[which(is.na(data1$chl))]=mean(data1$chl,na.rm = TRUE)
#checking
head(data1)## age bmi hyp chl
## 1 1 26.5625 <NA> 191.4
## 2 2 22.7000 1 187.0
## 3 1 26.5625 1 187.0
## 4 3 26.5625 <NA> 191.4
## 5 1 20.4000 1 113.0
## 6 3 26.5625 <NA> 184.0For binary class,or categorical we can impute using MICE//continous varaibel can be imputed with mice too.
#checking the available imputation function
?mice
#or
methods(mice)## Warning in .S3methods(generic.function, class, envir): function 'mice' appears
## not to be S3 generic; found functions that look like S3 methods## [1] mice.impute.2l.bin mice.impute.2l.lmer
## [3] mice.impute.2l.norm mice.impute.2l.pan
## [5] mice.impute.2lonly.mean mice.impute.2lonly.norm
## [7] mice.impute.2lonly.pmm mice.impute.cart
## [9] mice.impute.jomoImpute mice.impute.lasso.logreg
## [11] mice.impute.lasso.norm mice.impute.lasso.select.logreg
## [13] mice.impute.lasso.select.norm mice.impute.lda
## [15] mice.impute.logreg mice.impute.logreg.boot
## [17] mice.impute.mean mice.impute.midastouch
## [19] mice.impute.mnar.logreg mice.impute.mnar.norm
## [21] mice.impute.norm mice.impute.norm.boot
## [23] mice.impute.norm.nob mice.impute.norm.predict
## [25] mice.impute.panImpute mice.impute.passive
## [27] mice.impute.pmm mice.impute.polr
## [29] mice.impute.polyreg mice.impute.quadratic
## [31] mice.impute.rf mice.impute.ri
## [33] mice.impute.sample mice.mids
## [35] mice.theme
## see '?methods' for accessing help and source code#use original dataset
#loading inbuilt data
data2=nhanes
#checking the 1st 6 rows
head(data2)## age bmi hyp chl
## 1 1 NA NA NA
## 2 2 22.7 1 187
## 3 1 NA 1 187
## 4 3 NA NA NA
## 5 1 20.4 1 113
## 6 3 NA NA 184#convert hype to a factor
data2$hyp=as.factor(data2$hyp)
#confirming the canges
is.factor(data2$hyp)## [1] TRUE#Mice imputation (use chain imputaion, apply lot of diff statistical function to specific col)
#creating a function
library(mice)
my_imp=mice(data2, m=5, method=c("","pmm","logreg","pmm"),maxit=20)# you have to apply the methods you feel is ok to each column. for the column without missing value do not impute##
## iter imp variable
## 1 1 bmi hyp chl
## 1 2 bmi hyp chl
## 1 3 bmi hyp chl
## 1 4 bmi hyp chl
## 1 5 bmi hyp chl
## 2 1 bmi hyp chl
## 2 2 bmi hyp chl
## 2 3 bmi hyp chl
## 2 4 bmi hyp chl
## 2 5 bmi hyp chl
## 3 1 bmi hyp chl
## 3 2 bmi hyp chl
## 3 3 bmi hyp chl
## 3 4 bmi hyp chl
## 3 5 bmi hyp chl
## 4 1 bmi hyp chl
## 4 2 bmi hyp chl
## 4 3 bmi hyp chl
## 4 4 bmi hyp chl
## 4 5 bmi hyp chl
## 5 1 bmi hyp chl
## 5 2 bmi hyp chl
## 5 3 bmi hyp chl
## 5 4 bmi hyp chl
## 5 5 bmi hyp chl
## 6 1 bmi hyp chl
## 6 2 bmi hyp chl
## 6 3 bmi hyp chl
## 6 4 bmi hyp chl
## 6 5 bmi hyp chl
## 7 1 bmi hyp chl
## 7 2 bmi hyp chl
## 7 3 bmi hyp chl
## 7 4 bmi hyp chl
## 7 5 bmi hyp chl
## 8 1 bmi hyp chl
## 8 2 bmi hyp chl
## 8 3 bmi hyp chl
## 8 4 bmi hyp chl
## 8 5 bmi hyp chl
## 9 1 bmi hyp chl
## 9 2 bmi hyp chl
## 9 3 bmi hyp chl
## 9 4 bmi hyp chl
## 9 5 bmi hyp chl
## 10 1 bmi hyp chl
## 10 2 bmi hyp chl
## 10 3 bmi hyp chl
## 10 4 bmi hyp chl
## 10 5 bmi hyp chl
## 11 1 bmi hyp chl
## 11 2 bmi hyp chl
## 11 3 bmi hyp chl
## 11 4 bmi hyp chl
## 11 5 bmi hyp chl
## 12 1 bmi hyp chl
## 12 2 bmi hyp chl
## 12 3 bmi hyp chl
## 12 4 bmi hyp chl
## 12 5 bmi hyp chl
## 13 1 bmi hyp chl
## 13 2 bmi hyp chl
## 13 3 bmi hyp chl
## 13 4 bmi hyp chl
## 13 5 bmi hyp chl
## 14 1 bmi hyp chl
## 14 2 bmi hyp chl
## 14 3 bmi hyp chl
## 14 4 bmi hyp chl
## 14 5 bmi hyp chl
## 15 1 bmi hyp chl
## 15 2 bmi hyp chl
## 15 3 bmi hyp chl
## 15 4 bmi hyp chl
## 15 5 bmi hyp chl
## 16 1 bmi hyp chl
## 16 2 bmi hyp chl
## 16 3 bmi hyp chl
## 16 4 bmi hyp chl
## 16 5 bmi hyp chl
## 17 1 bmi hyp chl
## 17 2 bmi hyp chl
## 17 3 bmi hyp chl
## 17 4 bmi hyp chl
## 17 5 bmi hyp chl
## 18 1 bmi hyp chl
## 18 2 bmi hyp chl
## 18 3 bmi hyp chl
## 18 4 bmi hyp chl
## 18 5 bmi hyp chl
## 19 1 bmi hyp chl
## 19 2 bmi hyp chl
## 19 3 bmi hyp chl
## 19 4 bmi hyp chl
## 19 5 bmi hyp chl
## 20 1 bmi hyp chl
## 20 2 bmi hyp chl
## 20 3 bmi hyp chl
## 20 4 bmi hyp chl
## 20 5 bmi hyp chlsummary(data2$bmi)## Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
## 20.40 22.65 26.75 26.56 28.93 35.30 9my_imp$imp$bmi## 1 2 3 4 5
## 1 30.1 30.1 22.0 27.2 30.1
## 3 35.3 27.2 27.4 30.1 29.6
## 4 22.5 21.7 22.5 20.4 21.7
## 6 28.7 27.4 21.7 25.5 22.7
## 10 30.1 22.0 22.7 30.1 25.5
## 11 35.3 28.7 21.7 22.0 27.2
## 12 28.7 24.9 22.7 27.4 22.7
## 16 29.6 35.3 35.3 26.3 22.5
## 21 27.2 30.1 28.7 22.0 20.4number 5 gives a better value.
#final imputation
clean_data2= complete(my_imp,5)
clean_data2## age bmi hyp chl
## 1 1 30.1 1 187
## 2 2 22.7 1 187
## 3 1 29.6 1 187
## 4 3 21.7 2 206
## 5 1 20.4 1 113
## 6 3 22.7 2 184
## 7 1 22.5 1 118
## 8 1 30.1 1 187
## 9 2 22.0 1 238
## 10 2 25.5 1 204
## 11 1 27.2 1 118
## 12 2 22.7 2 187
## 13 3 21.7 1 206
## 14 2 28.7 2 204
## 15 1 29.6 1 187
## 16 1 22.5 1 238
## 17 3 27.2 2 284
## 18 2 26.3 2 199
## 19 1 35.3 1 218
## 20 3 25.5 2 184
## 21 1 20.4 1 113
## 22 1 33.2 1 229
## 23 1 27.5 1 131
## 24 3 24.9 1 184
## 25 2 27.4 1 186