Please join us in-person or online for a Queensland Branch Meeting. The seminar will start at 5:00 pm. Details for the seminar are provided below.
TITLE: Structural Choice Modelling: An Extension and Generalisation of McFadden’s Multinomial Logit
SPEAKER: Assoc Prof Len Coote and Dr Thomas Magor, University of Queensland
TIME: 5:00 pm - 6:30 pm (AEST), Wednesday 28th June 2023
VENUE: Room 67-146 - Priestley Building, UQ St. Lucia Campus or Online (Zoom link will be sent with registration)
Please note that the seminar will be recorded and might be put on YouTube or similar platform.
ABSTRACT:
In 2000, Daniel McFadden – Professor Emeritus at UC Berkeley – was awarded the Nobel Prize in Economic Sciences for theory and analysis of discrete choice. McFadden’s model – multinomial logit – retrieves the aggregate preferences of decisions makers. Extensions of his model – the random coefficient and error component forms of mixed logit – in addition retrieve unobserved (latent) sources of preference heterogeneity. These models are estimated using maximum likelihood and maximum simulated likelihood approaches, respectively.
McFadden’s model and its extensions are used in applied economics, including environmental, health, and transport economics (and in quantitative marketing) – principally for forecasting demand for discrete choices. McFadden’s model and extensions of his model are fit to the microdata of individual choices. The microdata may be marketplace choices (“revealed preferences” – preferences revealed by marketplace choices) or choices among hypothetical alternatives in an experiment (“stated preferences”).
Our contribution – in a series of papers in the Journal of Choice Modelling – is the development of a very general and flexible form of mixed logit (or “structural choice model”). Structural choice modelling (SCM) is specifically designed to incorporate latent variables (representing unobserved sources of preference heterogeneity) and subsumes many existing choice models as special cases. Applications of SCM include the study of multiple data generation processes: dynamics, embedded experiments, complex decision making, and group decision making.
We think there are many potential collaboration opportunities with researchers in statistics. Some immediate opportunities may include: (1) exploring gradient-based methods for structural choice model estimation other than the standard Newton-Raphson method; (2) studying the performance of different estimation approaches for SCM (e.g., maximum simulated likelihood versus composite marginal likelihood); and (3) developing new estimation software for SCM (i.e., creating an R package that can be disseminated to researchers in applied economics).
SPEAKERS' BIO:
Assoc Prof Len Coote
Len Coote holds the rank of Associate Professor in The University of Queensland Business School. His primary academic contribution is to the study of economic choices, which are ubiquitous in marketing (e.g., consider the decisions to install solar panels, purchase private health insurance, and use toll roads—to name just a few). Together with his academic collaborators, he developed a very general and flexible model for studying decision making and choice. The model integrates the mathematics of Daniel McFadden's (UC Berkeley) conditional logistic regression and Karl Joreskog's (Uppsala) linear structural relations models.
Dr Thomas Magor
Dr Thomas Magor is interested in modelling consumer choice to uncover the hidden patterns in our decision making. Dr Thomas Magor is passionate about public transport, sustainable travel/tourism, mobility in cities, consumers use of technology and societal wellbeing. Their PhD studied complex decision making in public transport and air travel by using latent variable structural choice models to find patterns in consumer heterogeneity attributable to the choice context and account for these patterns using behavioural decision theory. After graduating, Dr Thomas Magor worked at the Japanese International Cooperation Agency Research Institute (JICA-RI) in Tokyo, Japan as a behavioural economist. They have since returned to the UQ Business Schools and is now focussed on developing the new business analytics major as part of the new Bachelor of Advanced Business (Honours) program.
@StatSocAus
