Skip to main content
Log in

The Mixed Logit model: The state of practice

  • Published:
Transportation Aims and scope Submit manuscript

Abstract

The mixed logit model is considered to be the most promising state of the art discrete choice model currently available. Increasingly researchers and practitioners are estimating mixed logit models of various degrees of sophistication with mixtures of revealed preference and stated choice data. It is timely to review progress in model estimation since the learning curve is steep and the unwary are likely to fall into a chasm if not careful. These chasms are very deep indeed given the complexity of the mixed logit model. Although the theory is relatively clear, estimation and data issues are far from clear. Indeed there is a great deal of potential mis-inference consequent on trying to extract increased behavioural realism from data that are often not able to comply with the demands of mixed logit models. Possibly for the first time we now have an estimation method that requires extremely high quality data if the analyst wishes to take advantage of the extended behavioural capabilities of such models. This paper focuses on the new opportunities offered by mixed logit models and some issues to be aware of to avoid misuse of such advanced discrete choice methods by the practitioner.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Armstrong P, Garrido R & Ortuzar J de D (2001) Confidence intervals to bound the value of time. Transportation Research 37E: 143-161.

    Google Scholar 

  • Ben-Akiva M & Bolduc D (1996) Multinomial probit with a logit kernel and a general parametric specification of the covariance structure. Working paper, Department of Civil and Environmental Engineering, MIT.

  • Bhat CR (2000) Flexible model structures for discrete choice analysis. In: Hensher DA & Button KJ (eds) Handbook of Transport Modelling, Volume 1, of Handbooks in Transport (pp 71-90). Oxford: Pergamon Press.

    Google Scholar 

  • Bhat CR (2001) Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model. Transportation Research 35B: 677-695.

    Google Scholar 

  • Bhat CR (in press) Simulation estimation of mixed discrete choice models using randomised and scrambled Halton sequences. Transportation Research.

  • Bhat CR & Castelar S (2002) A unified mixed logit framework for modeling revealed and stated preferences: formulation and application to congestion pricing analysis in the San Francisco Bay Area. Transportation Research 36B: 593-616.

    Google Scholar 

  • Boersch-Supan A & Hajvassiliou V (1990) Smooth unbiased multivariate probability simula-tors for maximum likelihood estimation of limited dependent variable models. Journal of Econometrics 58: 347-368.

    Google Scholar 

  • Brownstone D (2001) Discrete choice modelling for transportation. In Hensher DA (ed) Travel Behaviour Research: The Leading Edge (pp 97-124). Oxford: Pergamon Press.

    Google Scholar 

  • Brownstone D & Train K (1999) Forecasting new product penetration with flexible substitution patterns. Journal of Econometrics 89: 109-129.

    Google Scholar 

  • Brownstone D, Bunch DS & Train K (2000) Joint mixed logit models of stated and revealed preferences for alternative-fuel vehicles. Transportation Research 34B: 315-338.

    Google Scholar 

  • Carrasco JA & Ortuzar J de D (2002) Review and assessment of the nested logit model. Transport Reviews 22: 197-218.

    Google Scholar 

  • Daniels R & Hensher DA (2000) Valuation of environmental impacts of transportation projects: the challenge of self-interest proximity. Journal of Transport Economics and Policy 34 (May): 189-214.

    Google Scholar 

  • DeShazo JR & Fermo G (2002) Designing choice sets for stated preference methods: the effects of complexity on choice consistency. Journal of Environmental Economics and Management 44: 123-143.

    Google Scholar 

  • Evans M, Hastings N & Peacock B (1993) Statistical Distributions. New York: John Wiley and Sons.

    Google Scholar 

  • Geweke J, Keane M & Runkle D (1994) Alternative computational approaches to inference in the multinomial probit model. Review of Economics and Statistics LXXVI: 609-632.

    Google Scholar 

  • Greene WH (2002) Econometric Analysis, 5th edition. Englewood Cliffs: Prentice Hall.

    Google Scholar 

  • Greene WH & Hensher DA (2003) A latent class model for discrete choice analysis: contrasts with mixed logit. Transportation Research B.

  • Halton JH (1960) On the efficiency of certain quasi-random sequences of points in evaluating multidimensional integrals. Numerische Math 2: 84-90 and corrigenda 196.

    Google Scholar 

  • Hensher DA (2001a) Measurement of the valuation of travel time savings. Journal of Transport Economics and Policy (Special Issue in Honour of Michael Beesley) 35: 71-98.

    Google Scholar 

  • Hensher DA (2001b) The valuation of commuter travel time savings for car drivers in New Zealand: evaluating alternative model specifications. Transportation 28, 101-118.

    Google Scholar 

  • Hensher DA & Greene WH (2002) Taking advantage of priors in estimation and posteriors in application to reveal individual-specific parameter estimates in mixed logit models. Institute of Transport Studies Working Paper. The University of Sydney, September.

  • Hensher, D.A. and Johnson, L.W. (1981) Applied Discrete Choice Modelling, Croom Helm (London) and Wiley (New York).

    Google Scholar 

  • Hensher DA, Louviere JJ & Swait J (1999) Combining sources of preference data. Journal of Econometrics 89: 197-221.

    Google Scholar 

  • Hensher DA & Sullivan C (2003) Willingness to pay for road curviness and road type for long distance travel in New Zealand. Transportation Research D.

  • Huber J & Train K (2001) On the similarity of classical and Bayesian estimates of individual mean partworths. Marketing Letters 12 (August): 259-270.

    Google Scholar 

  • Koop G & Poirier DJ (1993) Bayesian analysis of logit models using natural conjugate priors. Journal of Econometrics 56: 323-340.

    Google Scholar 

  • Koppelman F & Sethi V (2000) Closed-form discrete-choice models. In: Hensher DA & Button KJ (eds) Handbook of Transport Modelling, Volume 1, of Handbooks in Transport (pp 211-222). Oxford: Pergamon Press.

    Google Scholar 

  • Louviere JJ & Hensher DA (2001) Combining sources of preference data. In: Hensher DA (ed) Travel Behaviour Research: The Leading Edge (pp 125-144). Oxford: Pergamon Press.

    Google Scholar 

  • Louviere JJ, Hensher DA & Swait JF (2000) Stated Choice Methods and Analysis. Cambridge: Cambridge University Press.

    Google Scholar 

  • Louviere J, Carson R, Ainslie A, Cameron T, DeShazo JR, Hensher D, Kohn R, Marley T & Street D (2002) Dissecting the random component of utility, Workshop Report for the Asilomar Invitational Choice Symposium, California. Marketing Letters 13(3): 177-194. 174

    Google Scholar 

  • McFadden D (2001) Disaggregate Behavioural Travel Demand's RUM Side - A 30 years retrospective. In: Hensher DA (ed) Travel Behaviour Research: The Leading Edge (pp 17-64). Oxford: Pergamon Press.

    Google Scholar 

  • McFadden D & Ruud PA (1994) Estimation by simulation. Review of Economics and Statistics LXXVI(4): 591-608.

    Google Scholar 

  • McFadden D & Train K (2000) Mixed MNL models for discrete response. Journal of Applied Econometrics 15: 447-470.

    Google Scholar 

  • Revelt D & Train K (1998) Mixed Logit with repeated choices: households' choices of appliance efficiency level. Review of Economics and Statistics 80: 1-11.

    Google Scholar 

  • Rizzi LI & Ortuzar J de D (2002) Stated preference in the valuation of interurban road safety. Accident Analysis and Prevention, in press.

  • Sandor Z & Train K (2002) Quasi-random Simulation of Discrete Choice Models. Department of Economics, University of California at Berkeley, Berkeley.

    Google Scholar 

  • Stern S (1997) Simulation-based estimation. Journal of Economic Literature XXXV (December), 2006-2039.

    Google Scholar 

  • Swait J & Adamowicz W (2001) Choice complexity and decision strategy selection. Journal of Consumer Research 28: 135-148.

    Google Scholar 

  • Train K (1997) Mixed logit models for recreation demand. In: Kling C & Herriges J (eds) Valuing the Environment Using Recreation Demand Models. New York: Elgar Press.

    Google Scholar 

  • Train K (1998) Recreation demand models with taste differences over people. Land Economics 74: 230-239

    Google Scholar 

  • Train K (1999) Halton Sequences for Mixed Logit. Working paper. Department of Economics, University of California, Berkeley.

    Google Scholar 

  • Train K (2001) A comparison of hierarchical Bayes and maximum simulated likelihood for mixed logit, Paper presented at the Asilomar Invitational Choice Symposium, California, June.

  • Train K (2003), Discrete Choice Methods with Simulation. Cambridge: Cambridge University Press.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Hensher, D.A., Greene, W.H. The Mixed Logit model: The state of practice. Transportation 30, 133–176 (2003). https://doi.org/10.1023/A:1022558715350

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1022558715350

Navigation