A regression is only as good as the checks behind it. This skill teaches statsmodels as the tool that reports not just a coefficient but how far to trust it, with short checks (numbers you compute, steps you order, concepts you match) and finance examples: why a precise beta can come with a small R-squared, what a Durbin–Watson statistic and a variance inflation factor warn about, why overlapping returns inflate a t-statistic and how Newey–West fixes it, why a significant logit slope can be useless for trading, what a VAR and a Granger test can and cannot say, how a Kalman filter tracks a hidden level, why two prices that look cointegrated often are not, how quantile regression follows the tails of returns and why Fama–MacBeth beats a pooled regression. The capstone is a code lab where you build the two-pass procedure, a Newey–West t-statistic and an alpha test on real stocks.
Comfort with Python, NumPy and pandas is expected, together with basic statistics (mean, variance, correlation, hypothesis tests).
