nep-dcm New Economics Papers
on Discrete Choice Models
Issue of 2017‒08‒13
two papers chosen by
Edoardo Marcucci
Università degli studi Roma Tre

  1. The impact of the soccer schedule on TV viewership and stadium attendance: evidence from the Belgian Pro League By Chang Wang; Dries Goossens; Martina Vandebroek
  2. Estimating the mixed logit model by maximum simulated likelihood and hierarchical Bayes By Deniz Akinc; Martina Vandebroek

  1. By: Chang Wang; Dries Goossens; Martina Vandebroek
    Abstract: In the past decade, television broadcasters have been investing a huge amount of money for the Belgian Pro League broadcasting rights. These companies pursue an audience rating maximization, which depends heavily on the schedule of the league matches. At the same time, clubs try to maximize their home attendance and find themselves affected by the schedule as well. Our paper aims to capture the Belgian soccer fans’ preferences with respect to scheduling options, both for watching matches on TV and in the stadium. We carried out a discrete choice experiment using an online survey questionnaire distributed on a national scale. The choice sets are based on three match characteristics: month, kickoff time, and quality of the opponent. The first part of this survey concerns television broadcasting aspects. The second part includes questions about stadium attendance. The choice data is first analyzed with a conditional logit model which assumes homogenous preferences. Then a mixed logit model is fit to model the heterogeneity among the fans. The estimates are used to calculate the expected utility of watching a Belgian Pro League match for every possible setting, either on TV or in the stadium. These predictions are validated in terms of the real audience rating and home attendance data. Our results can be used to improve the scheduling process of the Belgian Pro League in order to persuade more fans to watch the matches on TV or in a stadium.
    Keywords: Audience ratings, Belgian soccer, Conditional logit model, Discrete choice experiment, Mixed logit model, Schedule, Stadium attendance
    Date: 2017–07
  2. By: Deniz Akinc; Martina Vandebroek
    Abstract: In this study, we compare the parameter estimates of the mixed logit model obtained with maximum likelihood and with hierarchical Bayesian estimation. The choice of the priors in Bayesian estimation and of the type and the number of quasi-random draws for maximum likelihood estimation have a big impact on the estimates. Our main focus is on the effect of the prior for the covariance matrix in hierarchical Bayes estimation. We investigate several priors such as Inverse Wisharts, the Separation Strategy, Scaled Inverse Wisharts and the Huang Half-t priors and we compute the root mean square errors of the resulting estimates for the mean, covariance matrix and individual parameters in a large simulation study. We show that the default settings in many software packages can lead to very unreliable results and that it is important to check the robustness of the results.
    Keywords: Mixed Logit Model, Hierarchical Bayesian Estimation, Separation Strategy, Inverse Wishart Distribution, Scaled Inverse Wishart Distribution, Huang Half-t Distribution
    Date: 2017–07

This nep-dcm issue is ©2017 by Edoardo Marcucci. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.