Combining estimates of interest in prognostic modelling studies after multiple imputation: current practice and guidelines
By Andrea Marshall, Douglas G. Altman, Roger Holder, Patrick Royston. BMC Medical Research Methodology, 2009
815 citations recorded by the source corpus.
BackgroundMultiple imputation (MI) provides an effective approach to handle missing covariate data within prognostic modelling studies, as it can properly account for the missing data uncertainty. The multiply imputed datasets are each analysed using standard prognostic modelling techniques to obtain the estimates of interest. The estimates from each imputed dataset are then combined into one overall estimate and variance, incorporating both the within and between imputation variability. Rubin's rules for combining these multiply imputed estimates are based on asymptotic theory. The resulting combined estimates may be more accurate if the posterior distribution of the population parameter of interest is better approximated by the normal distribution. However, the normality assumption may not be appropriate for all the parameters of interest when analysing prognostic modelling studies, such as predicted survival probabilities and model performance measures.MethodsGuidelines for combining the estimates of interest when analysing prognostic modelling studies are provided. A literature review is performed to identify current practice for combining such estimates in prognostic modelling studies.ResultsMethods for combining all reported estimates after MI were not well reported in the current literature. Rubin's rules without applying any transformations were the standard approach used, when any method was stated.ConclusionThe proposed simple guidelines for combining estimates after MI may lead to a wider and more appropriate use of MI in future prognostic modelling studies.
Subfields: Epidemiology, Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/f0445510f9820e036fe647f8e8f9aefd4bc1496a
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Epidemiology
In Statistics and Probability
- Julie Josse
- François Husson
- Xiang-Jun Zhou
- Jerome P. Reiter
- Vincent Audigier
- Joerg Drechsler
- Jes Frellsen
- Pierre-Alexandre Mattei
Citations in the corpus
- Multiple imputation for continuous variables using a Bayesian principal component analysis† (2014, background): “We detail hereafter themethodology described in [3,24] to combine the results from multiple imputed data sets under the assumption of an estimator normally distributed and evaluated on a large sample.”
- A Note on Bayesian Inference After Multiple Imputation (2010, methodology): “For example, in a literature review of applications of multiple imputation involving parameters not adequately modeled with normal distributions, Marshall et al. (2009) found that, “Rubin’s rules without applying any transformations were the standard approach used, when any method was stated.””