Applied Time Series Econometrics in Python and R
summary
Two-hour hands-on tutorial that derives ARIMAX and SARIMAX equations, shows ACF/PACF identification rules, and runs estimation and diagnostics in Python using statsmodels. Notebooks include a simulator widget for ARMA orders up to 4, example data (airline passengers, Dow returns, consumer sentiment, Citi stock, 10y yield), grid-search over dozens of models, and 5-step holdout forecasts that reveal rapid forecast degradation when only short lags are used. Covers transformations, stationarity tests, residual white-noise checks, AIC/BIC and out-of-sample RMSE.
AI-written summary · about
chapters (9)
- 0:00Time series econometrics intro
- 5:22Why study time series
- 8:56Common time series traits
- 14:48ARMA model simulator
- 25:07Exploratory data analysis
- 49:55Building ARMA models
- 1:11:58Seasonal ARIMA intro
- 1:27:29Model selection heuristics
- 1:37:11Practical model selection
related talks
29mTime Series Forecasting Techniques in Python
01h 27mBayesian Time Series
42mRobust Automated Forecasting in Python and R
29mSolving Forecasting Problems in R and Python
01h 30mTime Series Analysis with StatsModels
41mReliably forecasting time-series in real-time
26mTime Series Analysis in Python: Easy Tools for Scientific Insight
01h 43m(Serious) Time for Time Series