×

Alternating logistic regressions with improved finite sample properties. (English) Zbl 1372.62082

Summary: Alternating logistic regressions is an estimating equations procedure used to model marginal means of correlated binary outcomes while simultaneously specifying a within-cluster association model for log odds ratios of outcome pairs. A recent generalization of alternating logistic regressions, known as orthogonalized residuals, is extended to incorporate finite sample adjustments in the estimation of the log odds ratio model parameters for when there is a moderately small number of clusters. Bias adjustments are made both in the sandwich variance estimators and in the estimating equations for the association parameters. The proposed methods are demonstrated in a repeated cross-sectional cluster trial to reduce underage drinking in the United States, and in an analysis of dental caries incidence in a cluster randomized trial of 30 aboriginal communities in the Northern Territory of Australia. A simulation study demonstrates improved performance with respect to bias and coverage of their estimators relative to those based on the uncorrected orthogonalized residuals procedure.

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62J12 Generalized linear models (logistic models)
62H12 Estimation in multivariate analysis
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Carey, Modelling multivariate binary data with alternating logistic regressions, Biometrikan 80 pp 517– (1993) · Zbl 0800.62446 · doi:10.1093/biomet/80.3.517
[2] Divaris, Surface-specific efficacy of fluoride varnish in caries prevention in the primary dentition: Results of a community randomized clinical trial, Caries Research 47 pp 78– (2012) · doi:10.1159/000344015
[3] Emrich, On some small sample properties of generalized estimating equation estimates for multivariate dichotomous outcomes, Journal of Statistical Computation and Simulation 41 pp 19– (1992) · doi:10.1080/00949659208811388
[4] Evans, A comparison of generalized linear mixed model procedures with estimating equations for variance and covariance parameter estimation in longitudinal studies and group randomized trials, Statistics in Medicine 20 pp 3353– (2001) · doi:10.1002/sim.991
[5] Kauermann, A Note on the Efficiency of Sandwich Covariance Matrix Estimation, Journal of the American Statistical Association 96 pp 1387– (2001) · Zbl 1073.62539 · doi:10.1198/016214501753382309
[6] Liang, Longitudinal data analysis using generalized linear models, Biometrika 73 pp 13– (1986) · Zbl 0595.62110 · doi:10.1093/biomet/73.1.13
[7] Lu, A comparison of two bias-corrected covariance estimators for generalized estimating equations, Biometrics 63 pp 935– (2007) · Zbl 1147.62050 · doi:10.1111/j.1541-0420.2007.00764.x
[8] Mancl, A covariance estimator for GEE with improved small-sample properties, Biometrics 57 pp 126– (2001) · Zbl 1209.62310 · doi:10.1111/j.0006-341X.2001.00126.x
[9] Mardia, Some contributions to contingency-type bivariate, Biometrika 54 pp 235– (1967) · Zbl 0147.38104 · doi:10.1093/biomet/54.1-2.235
[10] Murray , D. M. 1998
[11] Preisser, Detecting patterns of occupational illness clustering with alternating logistic regressions applied to longitudinal data, American Journal of Epidemiology 158 pp 495– (2003a) · doi:10.1093/aje/kwg169
[12] Preisser, Deletion diagnostics for alternating logistic regressions, Biometrical Journal 54 pp 701– (2012) · Zbl 1400.62282 · doi:10.1002/bimj.201200002
[13] Preisser, Finite sample adjustments in estimating equations and covariance estimators for intracluster correlations, Statistics in Medicine 27 pp 5764– (2008) · doi:10.1002/sim.3390
[14] Preisser, Deletion diagnostics for marginal mean and correlation model parameters in estimating equations, Statistics and Computing 17 pp 381– (2007) · doi:10.1007/s11222-007-9031-1
[15] Preisser, Deletion diagnostics for generalised estimating equations, Biometrika 83 pp 551– (1996) · Zbl 0866.62041 · doi:10.1093/biomet/83.3.551
[16] Preisser, An integrated population-averaged approach to the design, analysis and sample size determination of cluster-unit trials, Statistics in Medicine 22 pp 1235– (2003b) · doi:10.1002/sim.1379
[17] Prentice, Correlated binary regression with covariates specific to each binary observation, Biometrics 44 pp 1033– (1988) · Zbl 0715.62145 · doi:10.2307/2531733
[18] Qaqish, A family of multivariate binary distributions for simulating correlated binary variables with specified marginal means and correlations, Biometrika 90 pp 455– (2003) · Zbl 1034.62042 · doi:10.1093/biomet/90.2.455
[19] Qaqish, Orthogonalized residuals for estimation of marginally specified association parameters in multivariate binary data, Scandinavian Journal of Statistics 39 pp 515– (2012) · Zbl 1323.62078 · doi:10.1111/j.1467-9469.2012.00802.x
[20] Reboussin, Geographic clustering of underage drinking and the influence of community characteristics, Drug and Alcohol Dependence 106 pp 38– (2010) · doi:10.1016/j.drugalcdep.2009.07.019
[21] Reboussin, Sample size estimation for alternating logistic regressions analysis of multilevel randomized community trials of under-age drinking, Journal of the Royal Statistical Society: Series A (Statistics in Society) 175 pp 691– (2012) · Zbl 06064208 · doi:10.1111/j.1467-985X.2011.01003.x
[22] Sharples, Regression analysis of correlated binary data: Some small sample results for the estimating equation approach, Journal of Statistical Computation and Simulation 42 pp 1– (1992) · Zbl 0775.62203 · doi:10.1080/00949659208811406
[23] Slade, Effect of health promotion and fluoride varnish on dental caries among Australian Aboriginal children: results from a community-randomized controlled trial, Community Dentistry and Oral Epidemiology 39 pp 29– (2011) · doi:10.1111/j.1600-0528.2010.00561.x
[24] Teerenstra, Sample size considerations for GEE analyses of three-level cluster randomized trials, Biometrics 66 pp 1230– (2010) · Zbl 1233.62190 · doi:10.1111/j.1541-0420.2009.01374.x
[25] Wolfson , M. Altman , D. DuRant , R. Shrestha , A. Patterson , T. E. Williams , A. 2004 National Evaluation of the Enforcing Underage Drinking Laws Program: Year 4 Report. Winston-Salem, NC: Wake Forest University School of Medicine, 2004 http://www.phsintranet.wfubmc.edu/EUDL2/pubs.cfm
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.