Forecasting Catch Time Series

This course will teach a number of standard approaches for forecasting from catch time series using the data and methods discussed in Stergiou and Christou (1996) Modelling and forecasting annual fisheries catches: comparison of regression, univariate and multivariate time series methods. Fisheries Research 25: 105-136.

Course Syllabus

• Time-varying regression
• Box-Jenkins (ARMA) Models
• Exponential smoothing
• Modelling time series with seasonality
• Forecast diagnostics and accuracy metrics

e-Text and other courses

An online book of the material is Fisheries Catch Forecasting. Links to our other workshops and courses on similar material can be found at the Applied Time Series Analysis website.

References

You can download the reference papers here. We are replicating (part of) the work in Stergio and Christou (1996) in the references.

---

—————————————-