Discrete Choice Methods and Their Applications In Preference Analysis of Vodka Consumers

Preference analysis is one of key elements in marketing researches and in economy in general. The preferences help to explain how and why consumers make their choices. There are two types of preferences – stated and revealed. Discrete choice methods allow to analyze stated preferences. They model choices made by people among a finite set of alternatives. Discrete choice models take many forms, including: binary logit, binary probit, multinomial logit, conditional logit, multinomial probit, nested logit, generalized extreme value models, mixed logit models, and exploded logit models. The main aim of the paper is to apply multinominal logit models to analyze vodka consumers preferences – a discrete choice experiment – with application of R software. The article presents basic terms of multinominal logit models, discrete choice experiment, model estimation. The paper presents also results of models estimation that will allow to determine worst and best vodka brands and which attributes are most important for consumers.