News‎ > ‎

New Edition of Practical Time Series Forecasting with R

posted Jul 26, 2016, 9:06 AM by Boaz Shmueli   [ updated Jul 27, 2016, 11:22 PM ]
Practical Time Series Forecasting with R, 3rd Edition
Practical Time Series Forecasting with R, Second Edition is now in print (a Kindle version is also available; an Indian Edition is coming soon). Here is a summary of the changes:

Based on feedback from readers and instructors, the Second Edition has two main improvements. First is a new-and-improved structuring of the topics. This reordering of topics is aimed at providing an easier introduction of forecasting methods which appears to be more intuitive to students. It also helps prioritize topics to be covered in a shorter course, allowing optional coverage of topics in Chapters 8-9. The restructuring also aligns this new edition with the new Third Edition of XLMiner®-based Practical Time Series Forecasting, offering instructors the flexibility to teach a mixed crowd of programmers and non-programmers. The re-ordering includes
  • relocating and combining the sections on autocorrelation, AR and ARIMA models, and external information into a separate new chapter (Chapter 7). The discussion of ARIMA models now includes equations and further details on parameters and structure
  • forecasting binary outcomes is now a separate chapter (Chapter 8), introducing the context of binary outcomes, performance evaluation, and logistic regression
  • neural networks are now in a separate chapter (Chapter 9)
The second update is the addition and expansion of several topics:
  • prediction intervals are now included on all relevant charts and a discussion of prediction cones was added
  • The discussion of exponential smoothing with multiple seasonal cycles in Chapter 5 has been extended, with examples using R functions dshw and tbats
  • Chapter 7 includes two new examples (bike sharing rentals and Walmart sales) using R functions tslm and stlm to illustrate incorporating external information into a linear model and ARIMA model. 
Additionally, the STL approach for decomposing a time series is introduced and illustrated.