eISSN: 2618-6446
Conferences Latest Issue Archive Future Issues About Us Journals

SETSCI - Volume (2018)
ISAS 2018 - Ist International Symposium on Innovative Approaches in Scientific Studies, Kemer-Antalya, Turkey, Apr 11, 2018

A Bayesian imputation approach for handling missing data in repeatedly measured categorical variables (ISAS 2018_270)
Oya Kalaycıoğlu1*
1Abant Izzet Baysal University , Bolu, Turkey
* Corresponding author: oyakalaycioglu@ibu.edu.tr
Published Date: 2018-06-23   |   Page (s): 440-442   |    46     3

ABSTRACT Multiple imputation (MI) is increasingly being used as a sophisticated tool to handle missing data in the recent years. The standard MI techniques use Bayesian sampling methods for making posterior draws for the imputations and analyse the imputed data sets under a frequentist framework. However, the software packages that are used to implement these techniques are not yet fully flexible to account for the non-normality of the incomplete variables in repeatedly measured data sets. Multiple imputation can be performed in a fully Bayesian modelling context, which offers a flexible alternative in terms of fitting hierarchical non-normal imputation models. This work is motivated by an observational cohort study which consists of different types of incomplete time-varying variables, such as skewed continuous, ordered and unordered categorical variables. These variables were imputed using hierarchical Bayesian imputation models, such as multivariate truncated normal, gamma, multinomial and logistic. The estimates of the analysis model obtained with fully Bayesian imputation method were compared to standard MI methods, which assume normality of the incomplete variables. In addition, the performance of the fully Bayesian imputation was evaluated with a simulation study, under different settings of incomplete data.  
KEYWORDS missing data, multiple imputation, Bayesian imputation, repeated measures, missing at random
REFERENCES [1] D.B. Rubin, Multiple imputation for nonresponse in surveys, New York: John Wiley, 1987.

[2] D. Lunn, N. Best, D. Spiegelhalter, G. Graham and B. Neuenschwander, “Combining MCMC with ‘sequential’ PKPD modelling,” J Pharmacokinet Pharmacodyn, vol. 36, pp. 19–38, 2009.

[3] J.L. Schafer, Analysis of incomplete multivariate data. London: Chapman and Hall, 1997.

[4] J. Carpenter and M. Kenward, Multiple imputation and its applications (Statistics in Practice). West Sussex: John Wiley and Sons, 2013.

[5] S. van Buuren and K. G. Oudshoorn, “MICE: Multivariate Imputation by Chained Equations in R,” Journal of Statistical Software, vol. 45.

[6] J. Nevalainen, M. G. Kenward and S. M. Virtanen, “Missing values illn longitudinal dietary data: A multiple imputation approach based on a fully conditional specification,” Statistics in Medicine, vol. 29, pp. 3657-3669, 2009.

[7] G. Carrigan, A. G. Barnett, A. J. Dobson and G. D. Mishra, “Compensating for Missing Data from Longitudinal Studies Using WinBugs,” Journal of Statistical Software, vol 19, 2007.

SET Technology - Turkey

eISSN  : 2618-6446

E-mail : info@set-science.com
+90 533 2245325

Tokat Technology Development Zone Gaziosmanpaşa University Taşlıçiftlik Campus, 60240 TOKAT-TURKEY
©2018 SET Technology