17
$\begingroup$

I am currently collecting data for an experiment into psychosocial characteristics associated with the experience of pain. As part of this, I am collecting GSR and BP measurements electronically from my participants, along with various self-report and implicit measures. I have a psychological background and am comfortable with factor analysis, linear models and experimental analysis.

My question is what are good (preferably free) resources available for learning about time series analysis. I am a total newb when it comes to this area, so any help would be greatly appreciated. I have some pilot data to practice on, but would like to have my analysis plan worked out in detail before I finish collected data.

If the provided references were also R related, that would be wonderful.

Edited: to change grammar and to add 'self report and implicit measures'

$\endgroup$

3 Answers 3

26
$\begingroup$

This is a very large subject and there are many good books that cover it. These are both good, but Cryer is my favorite of the two:

  1. Cryer. "Time Series Analysis: With Applications in R" is a classic on the subject, updated to include R code.
  2. Shumway and Stoffer. "Time Series Analysis and Its Applications: With R Examples".

A good free resource is Zoonekynd's ebook, especially the time series section.

My first suggestion for seeing the R packages would be the free ebook "A Discussion of Time Series Objects for R in Finance" from Rmetrics. It gives lots of examples comparing the different time series packages and discusses some of the considerations, but it doesn't provide any theory.

Eric Zivot's "Modeling financial time series with S-PLUS" and Ruey Tsay's "Analysis of Financial Time Series" (available in the TSA package on CRAN) are directed and financial time series but both provide good general references. I strongly recommend looking at Ruey Tsay's homepage because it covers all these topics, and provides the necessary R code. In particular, look at the "Analysis of Financial Time Series", and "Multivariate Time Series Analysis" courses.

$\endgroup$
2
  • 1
    $\begingroup$ Thank you, especially for the Zoonekynd reference, i found that before but couldnt get back to it. $\endgroup$ Commented Jan 15, 2011 at 15:41
  • $\begingroup$ I had never seen Zoonekynd before, it is great! $\endgroup$ Commented Sep 5, 2013 at 9:24
6
$\begingroup$

Time Series Analysis and Its Applications: With R Examples by Robert H. Shumway and David S. Stoffer would be a great resource for the subject, but you may find a lot of useful blog entries (e.g. my favorite one: learnr) and tutorials (e.g. from the linked homepage) also on the Internet freely available .

On David Stoffer's homepage (linked above) you can find the example datasets used in the book's chapters, and others from the first and second editions with even sample chapters also.

$\endgroup$
3
  • $\begingroup$ Thank you for the links, the one to this PDF looks especially useful cran.r-project.org/doc/contrib/Farnsworth-EconometricsInR.pdf Not sure how i missed that. $\endgroup$ Commented Jan 15, 2011 at 14:32
  • $\begingroup$ I don't think that the LearnR blog has any time series references... $\endgroup$
    – Shane
    Commented Jan 15, 2011 at 14:34
  • $\begingroup$ I searched it for time-series, and got some stuff about ggplot2. Useful, but not really with i was looking for. $\endgroup$ Commented Jan 15, 2011 at 16:16
2
$\begingroup$

Very late answer from me, but I have found Introductory Time Series with R by Cowpertwaite and Metcalfe to be really useful for transitioning between BSc level analysis to MSc level stuff and professional work. Yes, it is a little basic, but there's good explanations and examples and some useful code.

EDIT: I should add that I've also found Cryer and Chan hugely useful too in line with the first answer.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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