A note on obtaining correct marginal predictions from a random intercepts model for binary outcomes

BMC Medical Research Methodology

Rumana Z. Omar¹  Shaun Seaman²  Gareth Ambler¹  Menelaos Pavlou¹ 

[1]Department of Statistical Science, University College London, Gower St., London WC1E 6BT, UK

[2]MRC Biostatistics Unit, Cambridge, UK

关键词: Calibration;    Marginal predictions;    Random effects model;   

Others  :  1222423
DOI  :  10.1186/s12874-015-0046-6

 received in 2015-02-05, accepted in 2015-07-06,  发布年份 2015

【 摘 要 】

Background

Clustered data with binary outcomes are often analysed using random intercepts models or generalised estimating equations (GEE) resulting in cluster-specific or ‘population-average’ inference, respectively.

Methods

When a random effects model is fitted to clustered data, predictions may be produced for a member of an existing cluster by using estimates of the fixed effects (regression coefficients) and the random effect for the cluster (conditional risk calculation), or for a member of a new cluster (marginal risk calculation). We focus on the second. Marginal risk calculation from a random effects model is obtained by integrating over the distribution of random effects. However, in practice marginal risks are often obtained, incorrectly, using only estimates of the fixed effects (i.e. by effectively setting the random effects to zero). We compare these two approaches to marginal risk calculation in terms of model calibration.

Results

In simulation studies, it has been seen that use of the incorrect marginal risk calculation from random effects models results in poorly calibrated overall marginal predictions (calibration slope <1 and calibration in the large ≠ 0) with mis-calibration becoming worse with higher degrees of clustering. We clarify that this was due to the incorrect calculation of marginal predictions from a random intercepts model and explain intuitively why this approach is incorrect. We show via simulation that the correct calculation of marginal risks from a random intercepts model results in predictions with excellent calibration.

Conclusion

The logistic random intercepts model can be used to obtain valid marginal predictions by integrating over the distribution of random effects.

【 授权许可】

   
2015 Pavlou et al.

【 图 表 】

Fig. 1.

【 参考文献 】

• [1]Diggle P, Heagerty P, Liang K-Y, Zeger S. Analysis of longitudinal data. Oxford University Press, Oxford; 2002.
• [2]Molenberghs G, Verbeke G. Models for discrete longitudinal data. Springer, New York; 2005.
• [3]Bouwmeester W, Twisk JW, Kappen TH, van Klei WA, Moons KG, Vergouwe Y. Prediction models for clustered data: comparison of a random intercept and standard regression model. BMC Med Res Methodol. 2013; 13:19. BioMed Central Full Text
• [4]Skrondal A, Rabe-Hesketh S. Prediction in multilevel generalized linear models. J R Stat Soc A Stat Soc. 2009; 172(3):659-687.
• [5]Rose CE, Hall DB, Shiver BD, Clutter ML, Borders B. A Multilevel Approach to Individual Tree Survival Prediction. Forest Sci. 2006; 52(1):31-43.
• [6]Hedeker D, Gibbons RD. Longitudinal data analysis. John Wiley & Sons, New Jersey; 2006.
• [7]Zeger SL, Liang KY, Albert PS. Models for longitudinal data: a generalized estimating equation approach. Biometrics. 1988; 44(4):1049-1060.
• [8]Eldridge SM, Ukoumunne OC, Carlin JB. The Intra-Cluster Correlation Coefficient in Cluster Randomized Trials: A Review of Definitions. Int Stat Rev. 2009; 77(3):378-394.
• [9]Steyerberg EW, Vickers AJ, Cook NR, Gerds T, Gonen M, Obuchowski N et al.. Assessing the Performance of Prediction Models A Framework for Traditional and Novel Measures. Epidemiology. 2010; 21(1):128-138.
• [10]Steyerberg EW, Eijkemans MJC, Habbema JDF. Application of Shrinkage Techniques in Logistic Regression Analysis: A Case Study. Stat Neerlandica. 2001; 55(1):76-88.
• [11]Seaman S, Pavlou M, Copas A. Review of methods for handling confounding by cluster and informative cluster size in clustered data. Stat Med. 2014; 33(30):5371-5387.
• [12]Neuhaus JM, McCulloch CE. Separating between- and within-cluster covariate effects by using conditional and partitioning methods. J R Stat Soc B. 2006; 68(5):859-872.
• [13]Neuhaus JM, McCulloch CE. Estimation of covariate effects in generalized linear mixed models with informative cluster sizes. Biometrika. 2011; 98(1):147-162.