Non-linear mixed logit

Andersen, Steffen; Harrison, Glenn; Lau, Morten; Rutstroem, Elisabet

Abstract

We develop an extension of the familiar linear mixed logit model to allowfor the direct estimation of parametric non-linear functions defined over structuralparameters. Classic applications include the estimation of coefficients of utilityfunctions to characterize risk attitudes and discounting functions to characterizeimpatience. There are several unexpected benefits of this extension, apart from theability to directly estimate structural parameters of theoretical interest.

Citation

Andersen, S., Harrison, G., Lau, M., & Rutstroem, E. (2011). Non-linear mixed logit

• Working Paper Type: Working Paper
• Publication Date: Jan 1, 2011
• Deposit Date: Dec 7, 2012
• Publicly Available Date: Dec 7, 2012
• Series Title: Durham University Business School Economics Finance Accounting Working Papers
• Public URL: https://durham-repository.worktribe.com/output/1699625
• Publisher URL: http://www.dur.ac.uk/business/faculty/working-papers/