Data Analysis: Patterns, Prediction and Causality is a textbook that covers the most important methods and tools data analysts need in the fields of business, economics and public policy. It provides integrated knowledge of methods traditionally scattered around econometrics, machine learning and practical business statistics. It covers data wrangling (organization and cleaning), exploratory data analysis, regression analysis, prediction using regression and tree-based models, and causal analysis of experimental data and observational data. Our textbook covers relatively few methods but helps students gain a a lot of practice and a deep intuitive understanding of those methods. We emphasize the correct interpretation of the results and their informative presentation.
We provide many case studies and data exercises to help students obtain working knowledge of the tools and methods we cover. The case studies use real-life data, and we show how we clean and organize raw data to arrive at clean and tidy data files that we use for analysis. We provide code that reproduce all of the case study results in the textbook, in R and Stata (Python codes are in the works).
Our textbook has 24 chapters, structured into four parts: