×

Testing inference from logistic regression models in data with unobserved heterogeneity at cluster levels. (English) Zbl 1167.62064

Summary: Clustering due to unobserved heterogeneity may seriously impact on inference from binary regression models. We examined the performance of the logistic and logistic-normal models for data with such clustering. The total variance of unobserved heterogeneity rather than the level of clustering determines the size of bias of the maximum likelihood (ML) estimator, for the logistic model. Incorrect specification of clustering as level 2, using the logistic-normal model, provides biased estimates of the structural and random parameters, while specifying level 1 provides unbiased estimates for the former, and adequately estimates the latter. The proposed procedure appeals to many research areas.

MSC:

62J12 Generalized linear models (logistic models)
62H30 Classification and discrimination; cluster analysis (statistical aspects)
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] DOI: 10.1080/01621459.1994.10476863 · doi:10.1080/01621459.1994.10476863
[2] DOI: 10.1016/S0304-4076(98)00055-4 · Zbl 0959.62116 · doi:10.1016/S0304-4076(98)00055-4
[3] DOI: 10.1111/j.1467-8276.2006.01020.x · doi:10.1111/j.1467-8276.2006.01020.x
[4] DOI: 10.1016/j.jeem.2004.05.009 · Zbl 1066.62039 · doi:10.1016/j.jeem.2004.05.009
[5] DOI: 10.1080/00036840500427460 · doi:10.1080/00036840500427460
[6] Ayis S. A. M., Modelling Unobserved Heterogeneity: Theoretical and Practical Aspects (1995)
[7] DOI: 10.1111/j.1468-0084.2007.00445.x · doi:10.1111/j.1468-0084.2007.00445.x
[8] DOI: 10.1002/0470036486 · Zbl 1136.62075 · doi:10.1002/0470036486
[9] DOI: 10.1093/aje/kwm165 · doi:10.1093/aje/kwm165
[10] DOI: 10.1080/00420980701426624 · doi:10.1080/00420980701426624
[11] DOI: 10.1023/A:1006493723125 · doi:10.1023/A:1006493723125
[12] DOI: 10.1111/j.1751-5823.2007.00024.x · Zbl 1379.62094 · doi:10.1111/j.1751-5823.2007.00024.x
[13] DOI: 10.1191/0962280204sm351ra · Zbl 1054.62132 · doi:10.1191/0962280204sm351ra
[14] DOI: 10.1080/01621459.1996.10476661 · doi:10.1080/01621459.1996.10476661
[15] DOI: 10.1002/sim.3034 · doi:10.1002/sim.3034
[16] DOI: 10.1081/STA-120024478 · Zbl 1131.62326 · doi:10.1081/STA-120024478
[17] DOI: 10.1093/ije/dyn080 · doi:10.1093/ije/dyn080
[18] DOI: 10.1080/0003684042000280526 · doi:10.1080/0003684042000280526
[19] DOI: 10.1371/journal.pmed.0050177 · doi:10.1371/journal.pmed.0050177
[20] Skinner C. J., Analysis of Complex Surveys (1989) · Zbl 0701.62018
[21] Steele F., Journal of the Royal Statistical Society Series A-Statistics in Society 171 pp 5– (2008)
[22] DOI: 10.1111/1467-985X.00156 · Zbl 04558316 · doi:10.1111/1467-985X.00156
[23] DOI: 10.1016/S1047-2797(97)00023-9 · doi:10.1016/S1047-2797(97)00023-9
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.