ARCH-GARCH Models Tour
summary
Overview gives concrete choices: uses Python with pandas-datareader to pull Tesla 2015–2020 returns, fits volatility models with the arch package, initially fits GARCH with p=3 q=3 then simplifies to GARCH(3,0) after several insignificant beta terms; evaluates with a 365‑day rolling forecast and short 7‑day forecasts. Result shows predicted conditional variance tracks jumpy returns reasonably well; examples include parameter values and model diagnostics so one can reproduce and judge fit.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:10Time series fundamentals
- 3:12ARCH and GARCH models
- 5:37ARCH model concepts
- 8:27ARCH process and applications
- 10:36ARCH simulation
- 15:10GARCH process and extensions
- 17:42Building ARCH/GARCH models
- 20:30Python with stock data
- 26:25Conclusion
related talks
01h 40mApplied Time Series Econometrics in Python and R
21m2D ARIMA, Capturing New Trends for Distant Time Horizons
01h 27mBayesian Time Series
29mSolving Forecasting Problems in R and Python
29mTime Series Forecasting Techniques in Python
01h 19mModel criticism with ArviZ
01h 30mTime Series Analysis with StatsModels
18mMichaelWeylandt