 |
|
|
||||
|
EPUNet is now finished.
This site is left active for historical reasons only.
| Home > ECHP > Projects and Publications > Search Results |
 |
| Measures of the explanatory power of general multivariate probit models | |
|
Language
|
English |
|
URL
|
http://www.iser.essex.ac.uk/epag/pubs/workpaps/pdf/2003-43.pdf
|
|
Abstract
|
In this paper R 2 -type measures of the explanatory power of multivariate linear and categorical probit models proposed in the literature are reviewed and their deficiencies are discussed. It is argued that a measure of the explanatory power should take into account the components which are explicitely modeled when a regression model is estimated while it should be indifferent to components not explicitely modeled. Based on this view three different measures for multivariate probit models are proposed. Results of a simulation study are presented designed to compare two measures in various situations and evaluate the BC a bootstrap technique for testing the hypothesis that the corresponding measure is zero and to calculate approximate confidence intervals. The BC a bootstrap technique turned out to work quite well for a wide range of situations, but may lead to misleading results if the true values of the corresponding measure is close to zero. Key words: Pseudo- R 2 ; Measure of explanatory power; Multivariate probit model; Panel model; Simulation study; Bootstrap confidence intervals." |
|
Reference
|
Spiess, M. & Tutz, G. (2002) ‘Measures of the explanatory power of general multivariate probit models’, EPAG Working Paper 2002-33. Colchester: University of Essex |
|
Authors
|
M. Spiess, G. Tutz |
|
Countries included
|
Unknown |
|
ECHP Waves
|
1994, 1995, 1996 |
|
Institutions Involved
|
Institute for Social and Economic Research, Essex |
|
Contact Details
|