The proportion of missing data should not be used to guide decisions on multiple imputation

Abstract

Objectives Researchers are concerned whether multiple imputation (MI) or complete case analysis should be used when a large proportion of data are missing. We aimed to provide guidance for drawing conclusions from data with a large proportion of missingness. Study Design and Setting Via simulations, we investigated how the proportion of missing data, the fraction of missing information (FMI), and availability of auxiliary variables affected MI performance. Outcome data were missing completely at random or missing at random (MAR). Results Provided sufficient auxiliary information was available; MI was beneficial in terms of bias and never detrimental in terms of efficiency. Models with similar FMI values, but differing proportions of missing data, also had similar precision for effect estimates. In the absence of bias, the FMI was a better guide to the efficiency gains using MI than the proportion of missing data. Conclusion We provide evidence that for MAR data, valid MI reduces bias even when the proportion of missingness is large. We advise researchers to use FMI to guide choice of auxiliary variables for efficiency gain in imputation analyses, and that sensitivity analyses including different imputation models may be needed if the number of complete cases is small.

Adverse childhood experiences, DNA methylation age acceleration, and cortisol in UK children: a prospective population-based cohort study

“…Variables included in our imputation model were those in our analyses (exposures, covariates, outcomes) or predictors of missingness. Predictors of missingness are auxiliary variables selected to inform the generation of unbiased estimates of missing values and to improve the missing at random assumption [43]. We included twelve auxiliary variables from the mothers' and partners' social history during pregnancy and nine auxiliary childhood adversity exposures not part of the WHO ACE International Questionnaire.…”

Comparison of Methods for Processing Missing Values in Large Sample Survey Data

“…Researchers in a variety of fields often concern what is the proper scope of application for MI in terms of the proportion of missing data [23]. In this paper we found 30% is the scope of MI.…”

“…The analysis models would be the same as other statistical model with complete data sets. Many studies indicated that the imputation model should contain all variables in the analysis model or any auxiliary variables relating with outcome variables likely to be used in the subsequent analyses [19,23]. For each of 30 simulation data sets and the data set K, taking Y 1 as the dependent variable and the others as the covariates for regression analysis.…”

Analyzing Missing Data in Perinatal Pharmacoepidemiology Research: Methodological Considerations to Limit the Risk of Bias

“…Recent research has also shown that the proportion of missing data should not be the major driver for the decision on how to handle missing data. 22 In fact, even when the extent of missing data is large, results can still be unbiased provided that the MAR assumption is met and methods to handle missing data have been adequately applied.…”