Semiparametric methods for response-selective and missing data problems inregression

Citation
Jf. Lawless et Jd. Kalbfleisch, Semiparametric methods for response-selective and missing data problems inregression, J ROY STA B, 61, 1999, pp. 413-438
Citations number
42
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Mathematics
Journal title
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
ISSN journal
1369-7412 → ACNP
Volume
61
Year of publication
1999
Part
2
Pages
413 - 438
Database
ISI
SICI code
1369-7412(1999)61:<413:SMFRAM>2.0.ZU;2-6
Abstract
Suppose that data are generated according to the model f(y\x; theta) g(x), where y is a response and x are covariates. We derive and compare semiparam etric likelihood and pseudo-likelihood methods for estimating a for situati ons in which units generated are not fully observed and in which it is impo ssible or undesirable to model the covariate distribution. The probability that a unit is fully observed may depend on y, and there may be a subset of covariates which is observed only for a subsample of individuals. Our key assumptions are that the probability that a unit has missing data depends o nly on which of a finite number of strata that (y, x) belongs to and that t he stratum membership is observed for every unit. Applications include case -control studies in epidemiology, field reliability studies and broad class es of missing data and measurement error problems. Our results make fully e fficient estimation of theta feasible, and they generalize and provide insi ght into a variety of methods that have been proposed for specific problems .