Data Analysis, Forecasting & Risk Analysis

3 units

This course introduces modern statistical and econometric methods for analyzing data, forecasting future outcomes, and quantifying risk in business applications. Emphasis is placed on empirical finance, with applications to stock returns, portfolios, asset pricing, and factor models, but the tools developed are broadly applicable across marketing, operations, and accounting. Students learn how to build, estimate, and compare models for time series and panel data using both frequentist and Bayesian approaches. Topics include regression modeling, model selection, predictive inference, multivariate models, and simulation-based methods for evaluating uncertainty. Forecasting and risk assessment are treated as central inferential problems, with attention to out-of-sample prediction and decision-making under uncertainty. Students work extensively with real financial data using R, an open-source statistical programming environment, and gain experience implementing models, producing forecasts, and interpreting results through hands-on assignments and projects. While the focus is practical, the course also develops the underlying statistical intuition needed to understand estimation, model comparison, and prediction in modern data-driven business settings.