Wild, C. J. Fitting prospective regression models to case-control data. (English) Zbl 0752.62081 Biometrika 78, No. 4, 705-717 (1991). Summary: We consider fitting prospective regression models to data obtained by case-control or response selective sampling from a finite population with known population totals in each response category. Maximum likelihood estimation is developed and compared with two pseudo-likelihood approaches. The relative efficiencies of the methods are explored in the special case of estimating the parameters of the proportional odds model for ordinal responses. For such applications the method of D. A. Hsieh, C. F. Manski and D. McFadden [J. Am. Stat. Assoc. 80, 651- 662 (1985; Zbl 0585.62177)], called ‘conditional maximum likelihood’, is shown to be essentially as efficient as maximum likelihood; the latter is considerably more difficult to implement. In contrast the use of a weighted estimate of the prospective likelihood can lead to a substantial loss of efficiency. Cited in 15 Documents MSC: 62P10 Applications of statistics to biology and medical sciences; meta analysis 62D05 Sampling theory, sample surveys Keywords:case-control studies; logistic regression; asymptotic normality; covariance matrices; fitting prospective regression models; response selective sampling; finite population; known population totals; Maximum likelihood estimation; pseudo-likelihood approaches; relative efficiencies; proportional odds model; ordinal responses; conditional maximum likelihood; weighted estimate; prospective likelihood Citations:Zbl 0585.62177 PDFBibTeX XMLCite \textit{C. J. Wild}, Biometrika 78, No. 4, 705--717 (1991; Zbl 0752.62081) Full Text: DOI