Conditional and Marginal Models: Another View
Lee, Youngjo ; Nelder, John A.
Statist. Sci., Tome 19 (2004) no. 1, p. 219-238 / Harvested from Project Euclid
There has existed controversy about the use of marginal and conditional models, particularly in the analysis of data from longitudinal studies. We show that alleged differences in the behavior of parameters in so-called marginal and conditional models are based on a failure to compare like with like. In particular, these seemingly apparent differences are meaningless because they are mainly caused by preimposed unidentifiable constraints on the random effects in models. We discuss the advantages of conditional models over marginal models. We regard the conditional model as fundamental, from which marginal predictions can be made.
Publié le : 2004-05-14
Classification:  Generalized linear model,  hierarchical generalized linear model,  joint modeling of mean and dispersion,  spatial correlation,  temporal correlation
@article{1105714159,
     author = {Lee, Youngjo and Nelder, John A.},
     title = {Conditional and Marginal Models: Another View},
     journal = {Statist. Sci.},
     volume = {19},
     number = {1},
     year = {2004},
     pages = { 219-238},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1105714159}
}
Lee, Youngjo; Nelder, John A. Conditional and Marginal Models: Another View. Statist. Sci., Tome 19 (2004) no. 1, pp.  219-238. http://gdmltest.u-ga.fr/item/1105714159/