Scribd
Upload
107 views68 pages

Journal of Statistical Software: MICE: Multivariate Imputation by Chained Equations in R

This document discusses multiple imputation techniques for handling missing data in statistical analysis. It includes examples of using mice(), with(), pool(), and other functions to perform multiple imputation on several datasets with missing values. Graphs and results are shown for imputed head circumference, weight, height and other variables across different numbers of imputations and iterations.

Uploaded by

You Safe
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
107 views68 pages

Journal of Statistical Software: MICE: Multivariate Imputation by Chained Equations in R

This document discusses multiple imputation techniques for handling missing data in statistical analysis. It includes examples of using mice(), with(), pool(), and other functions to perform multiple imputation on several datasets with missing values. Graphs and results are shown for imputed head circumference, weight, height and other variables across different numbers of imputations and iterations.

Uploaded by

You Safe
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 68

Journal of Statistical Software

incomplete data

imputed data

analysis results

pooled results

mice()

with()

pool()

data frame

mids

mira

mipo

bmi
20 25

30

35

9 7 10
150 200 250

chl

age 1.0 1.5 2.0 2.5 3.0

25 0 16 0 9 0 17 0 8 0 15 0 10 0
miss. in chl obs. in bmi miss. in bmi obs. in hyp miss. in hyp obs. in chl

250

chl

200

150

observed

Imputation number

'

'

Maturation sum score 4 0 5 10 15 20 Age (years) 6 8 10 12 14 16

` ` `

` `

Maturation sum score 4 0 5 10 15 20 Age (years) 6 8 10 12 14 16

hgt
30

hgt

mean

90

86

sd 5 10 iteration 15 20

82

15

20

25

10 iteration

15

20

wgt
10 15 20 25 30 30

wgt

mean

25

10

15

20

10 iteration

15

20

sd

10 iteration

15

20

bmi
18.6

bmi

mean

18.2

sd 17.4 17.8 5 10 iteration 15 20

2.6

3.0

3.4

10 iteration

15

20

hgt
35

hgt

90

mean

80

sd 5 10 iteration 15 20

70

20

25

30

10 iteration

15

20

wgt
90 60

wgt

mean

70

sd 50 30 5 10 iteration 15 20

20

40

10 iteration

15

20

bmi
100

bmi

mean

60

sd 5 10 iteration 15 20

40

20

20

60

10 iteration

15

20

hgt
97

hgt

mean

95

sd 93 91 5 10 iteration 15 20

22

26

30

10 iteration

15

20

wgt
45

wgt

mean

40

30

35

sd 5 10 iteration 15 20

25

35

10 iteration

15

20

bmi

bmi

mean

17.5

sd 5 10 iteration 15 20

16.5

10 iteration

15

20

hc
54.2 5.5

hc

mean

53.6

sd 5 10 iteration 15 20

53.0

4.5

5.0

10 iteration

15

20

gen
1.65 2.4

gen

mean

sd 5 10 iteration 15 20

1.45

2.0

1.55

2.2

10 iteration

15

20

phb

phb

mean

2.4

2.2

10 iteration

15

20

1.75

1.85

sd

10 iteration

15

20

tau 0.78 0.80 0.82 0.84 0.86 0.88 0.90

5 10 15 20 Iteration

Observed
30 40 50

Imputed
60 70

Imputation 4

Imputation 5

Density

Imputation 1

Imputation 2

Imputation 3

30

40

50

60

70

30

40

50

60

70

Head circumference

Observed

Imputed

60

Head circumference

50

40

0.00

0.05

0.10

0.15

0.20

0.25

0.30

Probability of missing head circumference

Observed

Imputed

Density
20

10

10

Residuals of regression of hc on propensity score

Journal of Statistical Software

You might also like