Partial Autocorrelation

Explore the concept of partial autocorrelation to understand the direct relationships between lagged observations in a time series. Learn how to interpret partial autocorrelation coefficients, differentiate them from autocorrelation, and apply tools like the statsmodels plot_pacf function to graph and analyze partial autocorrelation for effective time series modeling.

We'll cover the following...

The partial autocorrelation coefficient
- Autocorrelation vs. partial autocorrelation
- Inference
Partial autocorrelogram
- Implementation in statsmodels
Partial autocorrelation in the temperatures data

The partial autocorrelation coefficient

The partial autocorrelation coefficient $\lambda_j$ of a time series $y_t$ measures the linear relationship between observations that are $j$ periods apart, once the effect of all observations in between has been accounted for. In other words, $\lambda_j$ tells us how strong the impact that $y_{t-j}$ has on $y_t$ after subtracting the impact that observations $y_{t-j+1}, y_{t-j+2}, ..., y_{t-1}$ ...

1.Introduction to Time Series

2.The Basics of Time Series

3.Exploring Data

Project

4.The Properties of Time Series

5.ARIMA Models

6.On Prediction

7.Choosing, Fitting, and Evaluating Models

8.Conclusion

9.Appendix

Assessment

Project

Mock Interview

Partial Autocorrelation

The partial autocorrelation coefficient