Two Properties of the Nested Logit Model

TWO PROPERTIES OF THE NESTED LOGIT MODEL

Carlos F. Daganzo
Institute of Transportation Studies
University of California, Berkeley, CA 94720

and

Michael Kusnic
Marketing and Product Planning Staff
General Motors Corporation, Detroit, MI 48202

ABSTRACT

This paper presents simple formulae for the utility covariances of the nested logit (NL) model, and based on these defines a "scaled tree" that can be used as an aid for the interpretation of estimation results.

The paper also shows that the full information log- likelihood function of linear-in-the-parameters NL models is concave in the utility parameters. Thus, conditional on the scaling parameters, full information maximum likelihood (FIML) searches cannot get trapped in local maxima.

Go back to Carlos Daganzo's Publications Page

TWO PROPERTIES OF THE NESTED LOGIT MODEL

Carlos F. Daganzo Institute of Transportation Studies University of California, Berkeley, CA 94720 and Michael Kusnic Marketing and Product Planning Staff General Motors Corporation, Detroit, MI 48202

ABSTRACT

Document maintained on server: http://www.ce.berkeley.edu/ Last update 6/11/96

Carlos F. Daganzo
Institute of Transportation Studies
University of California, Berkeley, CA 94720

and

Michael Kusnic
Marketing and Product Planning Staff
General Motors Corporation, Detroit, MI 48202

Document maintained on server: http://www.ce.berkeley.edu/
Last update 6/11/96