Premium
Regressor and random‐effects dependencies in multilevel models
Author(s) -
Ebbes Peter,
Böckenholt Ulf,
Wedel Michel
Publication year - 2004
Publication title -
statistica neerlandica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.52
H-Index - 39
eISSN - 1467-9574
pISSN - 0039-0402
DOI - 10.1046/j.0039-0402.2003.00254.x
Subject(s) - independence (probability theory) , econometrics , monte carlo method , random effects model , computer science , multilevel model , statistics , machine learning , mathematics , meta analysis , medicine
The objectives of this paper are (1) to review methods that can be used to test for different types of random effects and regressor dependencies, (2) to present results from Monte Carlo studies designed to investigate the performance of these methods, and (3) to discuss estimation methods that can be used when some but not all of the random effects and regressor independence assumptions, are violated. Because current methods are limited in various ways, we will also present a list of open problems and suggest solutions for some of them. As we will show, the issue of regressor random‐effects independence has received some attention in the econometrics literature, but this important work has had little impact on current research practices in the social and behavioral sciences.