Vfrdtyky

I have a question about merging datasets after multiple imputation. I have created an example to explain my problem:

id <- c(1,2,3,4,5,6,7,8,9,10)

age <- c(60,NA,90,55,60,61,77,67,88,90)

bmi <- c(30,NA,NA,23,24,NA,27,23,26,21)

time <- c(62,88,85,NA,68,62,89,62,70,99)

dat <- data.frame(id, age, bmi, time)

dat



id <- c(1,2,3,4,5,6,7,8,9,10)

m1 <- c(60,78,90,55,60,61,77,67,88,90)

m2 <- c(30,44,35,23,24,22,27,23,26,21)

m3 <- c(62,88,85,78,68,62,89,62,70,99)

dat2 <- data.frame(id, m1, m2, m3)

dat2

I have two datasets, dat and dat2. The dataset dat contains missing variables, so I use multiple imputation to impute this dataset (package MICE):

library(mice)

impdat <- mice(dat, maxit = 0)

methdat <- impdat$method

preddat <- impdat$predictorMatrix

preddat["id",] <- 0

preddat[,"id"] <- 0

impdat <- mice(dat, method = methdat, predictorMatrix = preddat, seed =         

2018, maxit = 10, m = 5)

Now I want to merge the imputed dataset impdat with the dataset dat2. But that is were my problem arises. I tried the following:

completedat <- complete(impdat, include = T, action = 'long')

finaldat <- merge(completedat, dat2, by = "id")



finaldat <- as.mids(finaldat)

  Error in `[<-.data.frame`(`*tmp*`, j, value = c(61, 88)) : replacement has 2 rows, data has 1  

However, this gives me an error message. The merging is successful, because the dataframe completedat is what I want. The problem is that I cannot transform it back to a mids object.

I know I can add the variables from dat2 one by one. That does work:

completedat <- complete(impdat, include = T, action = 'long')

completedat$m1 <- dat2$m1

finaldat2 <- as.mids(completedat)

In this example, this is okay, because dat2 only has 4 variables. In my real data, I have approximately 200 variables that I want to add to my multiple imputed dataset, so I hope there is an easier way to add all those variables to my imputed dataset. Can somebody help me?

Wouldn't cbind work provided that you want to combine imputed and non-imputed data?

id <- c(1,2,3,4,5,6,7,8,9,10)

age <- c(60,NA,90,55,60,61,77,67,88,90)

bmi <- c(30,NA,NA,23,24,NA,27,23,26,21)

time <- c(62,88,85,NA,68,62,89,62,70,99)

dat <- data.frame(id, age, bmi, time)

dat



id <- c(1,2,3,4,5,6,7,8,9,10)

m1 <- c(60,78,90,55,60,61,77,67,88,90)

m2 <- c(30,44,35,23,24,22,27,23,26,21)

m3 <- c(62,88,85,78,68,62,89,62,70,99)

dat2 <- data.frame(id, m1, m2, m3)

dat2



# install.packages("mice")

library(mice)

impdat <- mice(dat, 

               seed = 2018, 

               maxit = 10, 

               m = 5)

impdat

# Class: mids

# Number of multiple imputations:  5 

# Imputation methods:

#   id   age   bmi  time 

# "" "pmm" "pmm" "pmm" 

# PredictorMatrix:

#   id age bmi time

# id    0   1   1    1

# age   1   0   1    1

# bmi   1   1   0    1

# time  1   1   1    0



impdat = complete(impdat)

impdat



# id age bmi time

# 1   1  60  30   62

# 2   2  60  24   88

# 3   3  90  24   85

# 4   4  55  23   89

# 5   5  60  24   68

# 6   6  61  24   62

# 7   7  77  27   89

# 8   8  67  23   62

# 9   9  88  26   70

# 10 10  90  21   99



final_data = cbind(impdat, dat2)

final_data

# id age bmi time id m1 m2 m3

# 1   1  60  30   62  1 60 30 62

# 2   2  60  24   88  2 78 44 88

# 3   3  90  24   85  3 90 35 85

# 4   4  55  23   89  4 55 23 78

# 5   5  60  24   68  5 60 24 68

# 6   6  61  24   62  6 61 22 62

# 7   7  77  27   89  7 77 27 89

# 8   8  67  23   62  8 67 23 62

# 9   9  88  26   70  9 88 26 70

# 10 10  90  21   99 10 90 21 99