Cluster effects and simultaneity in multilevel models
For small group sizes, the GLS estimator in multilevel models is biased and inconsistent when the random cluster effects are correlated with the regressors. A fixed effects approach, conditioning on the cluster effects, provides consistent estimates for the slope parameters. The two estimators are equivalent when group sizes are large. The same results obtain for two-stage estimation procedures that allow for some of the regressors to be simultaneously determined with the dependent variable. The GLS and fixed effects estimators are applied to data on acute care hospital utilization in the UK, allowing for health authority district effects. © 1997 John Wiley & Sons, Ltd.
Year of publication: |
1997
|
---|---|
Authors: | Blundell, Richard ; Windmeijer, Frank |
Published in: |
Health Economics. - John Wiley & Sons, Ltd., ISSN 1057-9230. - Vol. 6.1997, 4, p. 439-443
|
Publisher: |
John Wiley & Sons, Ltd. |
Saved in:
Saved in favorites
Similar items by person
-
Individual effects and dynamics in count data models
Blundell, Richard, (1999)
-
Estimation in dynamic panel data models: improving on the performance of the standard GMM estimator
Blundell, Richard, (2000)
-
Identifying demand for health resources using waiting times information
Blundell, Richard, (2000)
- More ...