Buschena, David: Generalized Expected Utility, Heteroscedastic Error, and Path Dependence in Risky Choice
World Conference Econometric Society, 2000, Seattle

David Buschena, Montana State University
David Zilberman, University of California Berkeley
Generalized Expected Utility, Heteroscedastic Error, and Path Dependence in Risky Choice
Session: C-2-26  Saturday 12 August 2000  by Buschena, David
We evaluate the fit of several generalized expected utility models under homoscedasticity and three different heteroscedastic error structures for the data set first reported in Hey and Orme (1994). Standard chi-squared tests are used for nested tests, and both the Akaike (1973) information criterion and its consistent version (Hurvich and Tsai, 1989) are used for non-nested ranking of these models. Generalized expected utility models lose much of their predictive dominance over expected utility when a heteroscedastic error structure is used. Indeed, for most respondents and under various heteroscedastic error structures, a generalized expected utility framework gives no significant improvement in model fit relative to expected utility. A testing framework is developed that explicitly accounts for the path-dependent nature of the model selection problem. Not only does the selection of preference models depend on the error structure assumed, but the reverse is also true: the selection of the error structure depends on the preference structure assumed.


File created by Jurgen Doornik with eswc2000.ox on 2-01-2001