A Pseudo Maximum Likelihood Approach to Multilevel Modelling of Survey Data

@article{kovacevic:rai:2003, abstract = {An application of the pseudo maximum likelihood method to estimation of a multilevel linear model fitted to the dependent observations coming from a finite population is demonstrated. The proposed approach provides a closed form solution for estimating of the model parameters. It is computationally simpler than the iterative procedures suggested in the literature (e.g., the iterative probability weighted least squares method of Pfeffermann et al. (Pfeffermann, D., Skinner, C.J., Holmes, D.J., Goldstein, H., Rasbash, J. (1998). Weighting for unequal selection probabilities in multilevel models. <i>Journal of Royal Statistical Society</i> B 60:23–40)). Issues related to model and sample design hierarchies and their impact on estimation are discussed. A problem of weighting at different levels is addressed. A small simulation study showed that the proposed procedure is efficient even for small within group sample sizes.}, author = {Kova\&ccaron;evi\&cacute;, Milorad S. and Rai, Shesh N. }, citeulike-article-id = {3158754}, doi = {http://dx.doi.org/10.1081/STA-120017802}, journal = {Communications in Statistics - Theory and Methods}, keywords = {multilevel, sampling, survey, weights}, number = {1}, pages = {103--121}, posted-at = {2008-08-27 17:38:10}, priority = {2}, publisher = {Taylor \& Francis}, title = {A Pseudo Maximum Likelihood Approach to Multilevel Modelling of Survey Data}, url = {http://dx.doi.org/10.1081/STA-120017802}, volume = {32}, year = {2003} }

TY - JOUR ID - kovacevic:rai:2003 L3 - citeulike-article-id:3158754 N2 - An application of the pseudo maximum likelihood method to estimation of a multilevel linear model fitted to the dependent observations coming from a finite population is demonstrated. The proposed approach provides a closed form solution for estimating of the model parameters. It is computationally simpler than the iterative procedures suggested in the literature (e.g., the iterative probability weighted least squares method of Pfeffermann et al. (Pfeffermann, D., Skinner, C.J., Holmes, D.J., Goldstein, H., Rasbash, J. (1998). Weighting for unequal selection probabilities in multilevel models. <i>Journal of Royal Statistical Society</i> B 60:23–40)). Issues related to model and sample design hierarchies and their impact on estimation are discussed. A problem of weighting at different levels is addressed. A small simulation study showed that the proposed procedure is efficient even for small within group sample sizes. IS - 1 JF - Communications in Statistics - Theory and Methods EP - 121 TI - A Pseudo Maximum Likelihood Approach to Multilevel Modelling of Survey Data PB - Taylor & Francis VL - 32 SP - 103 KW - multilevel KW - sampling KW - survey KW - weights AU - Kova&ccaron;evi&cacute;, Milorad AU - Rai, Shesh PY - 2003/// UR - http://dx.doi.org/10.1081/STA-120017802 ER -