DOI: 10.2307/145818
关键词: Latent variable model 、 Sampling process 、 Selection (genetic algorithm) 、 Statistics 、 Regression 、 Mathematics 、 Simple (abstract algebra)
摘要: This article considers anew the problem of estimating a regression E(y|x) when realizations (y, x) are sampled randomly but y is observed selectively. The central issue failure sampling process to identify E(y|x). faced by researcher find correct prior restrictions which, combined with data, regression. Two kinds examined here. One, which has not been studied before, bound on support y. Such implies simple, useful other, received much attention, separability restriction derived from latent variable model.