Back

Multiple imputation assuming missing at random: auxiliary imputation variables that only predict missingness can increase bias due to data missing not at random

2023-10-17 epidemiology Title + abstract only
View on medRxiv
Show abstract

Epidemiological studies often have missing data, which are commonly handled by multiple imputation (MI). MI is valid (given correctly-specified models) if data are missing at random, conditional on the observed data, but not (unless additional information is available) if data are missing not at random (MNAR). In this paper we explore a previously-suggested strategy, namely, including an auxiliary variable predictive of missingness but not the missing data in the imputation model, when data are ...

Predicted journal destinations

1
PLOS ONE
1737 training papers
Top 57% 10.9%
2
PLOS Computational Biology
141 training papers
Top 2% 7.2%
3
American Journal of Epidemiology
54 training papers
#1 7.2%
4
Nature Communications
483 training papers
Top 19% 5.9%
5
Scientific Reports
701 training papers
Top 52% 5.5%
6
Epidemics
96 training papers
Top 2% 5.5%
7
International Journal of Epidemiology
65 training papers
Top 0.8% 5.5%
8
Proceedings of the National Academy of Sciences
100 training papers
Top 2% 4.6%
9
BMC Medicine
155 training papers
Top 4% 4.6%
10
BMC Medical Research Methodology
41 training papers
Top 0.7% 3.6%
11
Journal of The Royal Society Interface
54 training papers
Top 1% 3.6%
12
Epidemiology
26 training papers
Top 0.1% 2.8%
13
eLife
262 training papers
Top 16% 2.8%
14
Science
46 training papers
Top 2% 1.8%
15
European Journal of Epidemiology
36 training papers
Top 1% 1.8%
16
Royal Society Open Science
49 training papers
Top 2% 1.8%
17
BMC Public Health
148 training papers
Top 24% 1.2%
18
Statistics in Medicine
17 training papers
Top 0.2% 1.2%
19
Bulletin of Mathematical Biology
17 training papers
Top 0.7% 1.1%
20
Epidemiology and Infection
80 training papers
Top 11% 1.1%
21
PLOS Genetics
39 training papers
Top 7% 0.9%
22
Journal of Theoretical Biology
29 training papers
Top 3% 0.9%
23
BMJ Open
553 training papers
Top 65% 0.9%
24
PLOS Medicine
95 training papers
Top 19% 0.9%
25
Clinical Infectious Diseases
219 training papers
Top 24% 0.9%
26
BMC Infectious Diseases
110 training papers
Top 23% 0.9%
27
Eurosurveillance
77 training papers
Top 16% 0.7%
28
Infectious Disease Modelling
50 training papers
Top 8% 0.7%
29
Science Advances
52 training papers
Top 7% 0.7%