IBM Support

Which type of Markov Chain Monte Carlo method is used in multiple inputation?

Troubleshooting


Problem

The Algorithms material for the Multiple Imputation procedure in SPSS/PASW Statistics chapter for Multiple Imputation (MI) states that the Fully Conditional Specification (FCS) method uses an iterative Markov Chain Monte Carlo (MCMC) method Does FCS employ one of the common MCMC methods, such as Gibbs Sampler, Data Augmentation, or Metropolis-Hastings?

Resolving The Problem

The FCS method corresponds to the Gibbs Sampler under the assumption that the conditional distribution exists.

The following papers provide background material on the FCS method of MCMC.

van Buren, S. (2007). Multiple imputation of discrete and continuous data by fully conditional specification. Statistical Methods in Medical Research, 16, 219-242.
http://www.stefvanbuuren.nl/publications/MI%20by%20FCS%20-%20SMMR%202007.pdf

van Buren, S., Boshuizen, H.C., & Knook, D.L. (1999). Multiple imputation of missing blood pressure covariates in survival analysis. Statistics in Medicine, 18, 681-694.
http://www.stefvanbuuren.nl/publications/Multiple%20imputation%20-%20Stat%20Med%201999.pdf

[{"Product":{"code":"SSLVMB","label":"IBM SPSS Statistics"},"Business Unit":{"code":"BU059","label":"IBM Software w\/o TPS"},"Component":"Not Applicable","Platform":[{"code":"PF025","label":"Platform Independent"}],"Version":"Not Applicable","Edition":"","Line of Business":{"code":"LOB10","label":"Data and AI"}}]

Historical Number

88690

Document Information

Modified date:
16 June 2018

UID

swg21488713

Page Feedback