5
$\begingroup$

I am wondering if anyone has book references for time series. I would like something comparable (in popularity) to the 'ESL' or to 'Machine learning' from Murphy in the machine learning field.

Does anyone knows what are the most complete (in term of methods scope) books containing all about exponential smoothing (all of them), arima, sarima , arch, garch, neural network for time series, kalman filters, ... etc ?

$\endgroup$
  • 1
    $\begingroup$ Please be very specific about what objective standards should be applied to determine "comparable," "good," and "best," for without such clear standards this question is off-topic here. Consult our help center for more information. $\endgroup$ – whuber Jan 27 '14 at 15:11
  • $\begingroup$ Is that precise enough now ? I'm really just looking for a recomendation for a complete time series book. Should I ask this question on stack exchange instead ? $\endgroup$ – Scratch Jan 27 '14 at 15:30
  • $\begingroup$ You wouldn't get far with this on SO! Because your modification provides a reasonably clear criterion for people to suggest answers, I have voted to reopen your question here. $\endgroup$ – whuber Jan 27 '14 at 15:33
  • $\begingroup$ I am new in Time Series and I was wondering why is that Time Series is not included on ESL (or any other book like this)? Time Series is a subfield of Statistical Learning, isn't it? $\endgroup$ – Laura Aug 21 at 20:04
7
$\begingroup$

I don't know of a single time series book that is as comprehensive as Elements of Statistical Learning. However, here's a list of a few books that i've found helpful:

Free online. More of a forecasting focus, but definitely a good starting point. The slides under resources are also helpful:

  • Hyndman, R. J., & Athanasopoulos, G. (2013). Forecasting: principles and practice. Retrieved from http://otexts.org/fpp/

Probably the most comprehensive. With information about many of the model types you've listed:

  • Shumway, R. H., & Stoffer, D. S. (2010). Time Series Analysis and Its Applications. Springer.

Definitive resource on exponential smoothing:

  • Hyndman, R., Koehler, A. B., Ord, J. K., & Snyder, R. D. (2008). Forecasting with Exponential Smoothing. Springer.
$\endgroup$
  • $\begingroup$ +1 for Shumway and Stoffer. My favourite, with frequency domain material, state space models, and R examples in later editions to boot. $\endgroup$ – conjugateprior Jan 29 '14 at 19:49
3
$\begingroup$

Brockwell and Davis wrote two excellent time series books. Both cover a great deal of material and the writing is very clear. The first book is more introductory, and the second one has a more mathematical development.

http://www.amazon.com/Introduction-Forecasting-Springer-Texts-Statistics/dp/0387953515/ http://www.amazon.com/Time-Series-Methods-Springer-Statistics/dp/1441903194

$\endgroup$
1
$\begingroup$

I don't know about the 'ESL' or machine learning, but what about good ol' Tsay?

Some parts you mentioned are included, some not (e.g. Kalman filter):

When it comes to times series with applications and an easy-to-understand way of explaining he is my Tom Cruise, my top gun.

$\endgroup$
1
$\begingroup$

ESL is not for time series in my opinion. Tsay's book in addition to Cowpertwait's intro level book are the best combination.

$\endgroup$
  • $\begingroup$ No one said ESL was about time series... $\endgroup$ – Scratch Feb 10 '14 at 17:57
0
$\begingroup$

Have a look at

  • James D. Hamilton. Time Series Analysis. Princeton Univ. Press, Princeton, N.J, 1994.

It is very thorough. I'm not sure about neural networks and "all" exponential smoothing, but the rest is in there.

$\endgroup$
0
$\begingroup$

Here is a good list of books on time series analysis. Note that there is a lot of difference amongst books that cater to people of different backgrounds (economists/engineers/statisticians). hth

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.