A Methodology to Incorporate Managerial Intuition into A logit Model

In this paper we develop a novel methodology to incorporate managerial judgment or intuition into a logit model. The major contribution and focus of this research is on the way prior information is incorporated in our model. By extending the model introduced by Koop and Poirier (1993) we are able incorporate information about exogenous variables as priors in our model. The major advantage of this approach is that it facilitates the way prior information is included in a logit model. A manger can think in terms of changes in exogenous variables rather than unobservable parameters, as in a standard bayesian approach. We provide two empirical illustrations of our model; (i) showing the impact of a change in marketing strategy by including informative prior through ‘managers’ subjective judgments, (ii) forecast sales when limited information is available. Results indicate that incorporating subjective prior information may lead to a significant improvement of parameter estimates and sales forecasts.