Author:
Cai Mingyang,van Buuren Stef,Vink Gerko
Abstract
AbstractFully conditional specification (FCS) is a convenient and flexible multiple imputation approach. It specifies a sequence of simple regression models instead of a potential complex joint density for missing variables. However, FCS may not converge to a stationary distribution. Many authors have studied the convergence properties of FCS when priors of conditional models are non-informative. We extend to the case of informative priors. This paper evaluates the convergence properties of the normal linear model with normal-inverse gamma priors. The theoretical and simulation results prove the convergence of FCS and show the equivalence of prior specification under the joint model and a set of conditional models when the analysis model is a linear regression with normal inverse-gamma priors.
Publisher
Springer Science and Business Media LLC
Reference21 articles.
1. Rubin, D. B. Multiple Imputation for Nonresponse in Surveys, vol. 81 (John Wiley & Sons, 2004).
2. Schafer, J. L. Analysis of Incomplete Multivariate Data (Chapman and Hall/CRC, 1997).
3. Van Buuren, S. Flexible Imputation of Missing Data (CRC press, 2018).
4. Van Buuren, S. & Groothuis-Oudshoorn, K. Mice: Multivariate imputation by chained equations in r. J. Stat. Softw. 45, 1–68 (2010).
5. Van Buuren, S. Multiple imputation of discrete and continuous data by fully conditional specification. Stat. Methods Med. Res. 16, 219–242 (2007).