Time Series Analysis: Forecasting and Control by Box, George E. P., Jenkins, Gwilym M., Reinsel, Gregory C. 4th edition (2008) Hardcover

by George E.P. Box

This is a revision of a classic, seminal, and authoritative book that has been the model for most books on the topic written since 1970. It focuses on practical techniques throughout, rather than a rigorous mathematical treatment of the subject. It explores the building of stochastic (statistical) models for time series and their use in important areas of application —forecasting, model specification, estimation, modeling the effects of intervention events, and process control, among others. In addition to meticulous modifications in content and improvements in style, the new edition incorporates several new topics in an effort to modernize the subject matter. These topics include extensive discussions of multivariate time series, smoothing, likelihood function based on the state space model, autoregressive models, structural component models and deterministic seasonal components, and nonlinear and long memory models.

Genres: Nonfiction, Mathematics, Textbooks

Unknown Binding

First published June 30, 2008

Reviews

[David Lindelof · Rating 5 out of 5]

Probably one of the best textbooks on the subject out there. But first a disclaimer: I did not read this book cover to cover; however, I did skim through its entirety, fully reading those parts that were most applicable to my current work.

There's a very close relationship between the theory of time series and modern control theory, and the notation one finds in this book will be familiar to you if you have read textbooks on control theory before. Box takes however a bold step and doesn't really formally define what a Lorentz transform it; instead, he simply introduces the B shift operator and then uses it as the free variable in polynoms; something that other textbooks do only after carefully laying the theoretical grounds that "allow" you to do this sort of thing.

This has the advantage of making the subject much more accessible, without sacrificing any mathematical rigour. This book is, I would argue, THE essential textbook on time series analysis and definitely belongs on the bookshelf of anyone working with control systems, such as yours truly.

[Bala Vignesh]

took a while

[Suyash Mallik · Rating 4 out of 5]

Pretty engaging as far as textbooks go. will go through python implementations of some of the ideas mentioned here.