2. Exploratory Data Analysis

Exploratory Data Analysis (EDA) is an essential component of discrete choice modeling, enabling modelers to understand the underlying patterns and relationships in data. This chapter delves into various EDA techniques, including descriptive statistics, visualization, and bivariate and multivariate analysis. By exploring univariate and multivariate distributions, modelers can detect outliers, formulate hypotheses, and gain insights into individual behavior and implicit preferences. The chapter emphasizes the creative and playful nature of EDA, highlighting the importance of visualization in making data more accessible and interpretable. Through practical examples and code snippets, readers are guided through the process of EDA, from data cleaning to visualization and interpretation. The chapter underscores the need for a good understanding of EDA tools to ensure the quality of data entering the model and to facilitate the development of robust discrete choice models.