scispace - formally typeset
Search or ask a question

Showing papers on "Random effects model published in 1979"


Posted Content
TL;DR: In this paper, the joint maximum likelihood estimator of the structural parameters is not consistent as the number of groups increases, with a fixed number of observations per group, and a conditional likelihood function is maximized, conditional on sufficient statistics for the incidental parameters.
Abstract: In data with a group structure, incidental parameters are included to control for missing variables. Applications include longitudinal data and sibling data. In general, the joint maximum likelihood estimator of the structural parameters is not consistent as the number of groups increases, with a fixed number of observations per group. Instead a conditional likelihood function is maximized, conditional on sufficient statistics for the incidental parameters. In the logit case, a standard conditional logit program can be used. Another solution is a random effects model, in which the distribution of the incidental parameters may depend upon the exogenous variables.

2,338 citations


Journal ArticleDOI
TL;DR: In this paper, the authors considered the question of a proper forecast in the context of the variance-components model and showed how residuals from the estimated equation should be included in the forecast.

52 citations


Journal ArticleDOI
TL;DR: In this article, some ANOVA models are presented where the treatment effects can assume, under the alternative, a few discrete values with prescribed probabilities, and the power function, of the test that all treatment effects are zero, is approximated by a Laguerre series using the methods of Tiku (1965).

9 citations



Posted Content
TL;DR: In this paper, the joint maximum likelihood estimator of the structural parameters is not consistent as the number of groups increases, with a fixed number of observations per group, and a conditional likelihood function is maximized, conditional on sufficient statistics for the incidental parameters.
Abstract: In data with a group structure, incidental parameters are included to control for missing variables. Applications include longitudinal data and sibling data. In general, the joint maximum likelihood estimator of the structural parameters is not consistent as the number of groups increases, with a fixed number of observations per group. Instead a conditional likelihood function is maximized, conditional on sufficient statistics for the incidental parameters. In the logit case, a standard conditional logit program can be used. Another solution is a random effects model, in which the distribution of the incidental parameters may depend upon the exogenous variables.

3 citations


Journal ArticleDOI
TL;DR: In this article, the concept of a random factor is discussed along with its application to and relevance for modeling research, and a practical solution to the problem is proposed, where the experimenter conceptualizes a study as providing the basis for a generalization to a larger population of models.
Abstract: SCHEIRER, C. JAMES, and GELLER, SANFORD E. The Analysis of Random Effects in Modeling Studies. CHILD DEVELOPMENT, 1979, 50, 752-757. Much of the research on modeling has used single models or, when multiple models have been used, a questionable data analysis has been applied. The analytic and conceptual difficulty revolves around the decision whether to treat models as a fixed or as a random factor in the analysis. We argue that in almost all cases the experimenter conceptualizes a study as providing the basis for a generalization to a larger population of models. Since this is the case, models must be analyzed as a random factor or a positive bias is introduced into the results. In this paper the concept of a random factor is discussed along with its application to and relevance for modeling research. Worked examples are provided, and a practical solution to the problem is proposed.

2 citations


Journal ArticleDOI
TL;DR: In this article, the authors consider the effects of departure from normality on the classical JT-tests for variance components and show that the departure has little effect on the type 1 error and the power function.
Abstract: In this paper we consider the following nested random effect model where the αi's, the βij's and the eijk are independent random variables. By assuming that these variables follow a mixture of two normal densities, we study the effects of departure from normality on the classical JT-tests for variance components. It is shown that the departure from normality has little effects on the type 1 error and the power function; this indicates that the classical F-tests are quite robust with respect to departure from normality.