Two-Step Hierarchical Estimation: Beyond Regression Analysis
Author:
- Christopher H. AchenCAChristopher H. Achen
- 1 January 2005
- journal article
- Published by Cambridge University Press (CUP) in Political Analysis
- Vol. 13 (4) , 447-456
Abstract
Two-step estimators for hierarchical models can be constructed even when neither stage is a conventional linear regression model. For example, the first stage might consist of probit models, or duration models, or event count models. The second stage might be a nonlinear regression specification. This note sketches some of the considerations that arise in ensuring that two-step estimators are consistent in such cases.Keywords
This publication has 15 references indexed in Scilit:
- Context and the Economic Vote: A Multilevel AnalysisPolitical Analysis, 2005
- EDA for HLM: Visualization when Probabilistic Inference FailsPolitical Analysis, 2005
- Applying a Two-Step Strategy to the Analysis of Cross-National Public Opinion DataPolitical Analysis, 2005
- How Diffusion of Power in Parliaments Affects Voter ChoicePolitical Analysis, 2005
- Causal Heterogeneity in Comparative Research: A Bayesian Hierarchical Modelling ApproachAmerican Journal of Political Science, 1998
- Random Effects Probit and Logistic Regression Models for Three-Level Data1997
- Pooling Disparate ObservationsAmerican Journal of Political Science, 1996
- A two-stage estimator for probit models with structural group effectsJournal of Econometrics, 1994
- Regression Diagnostics1980
- Regressions from Samples Having Different CharacteristicsReview of Economics and Statistics, 1977