[R-sig-eco] Time series analysis: moving average (MA) models with transfer functions

[Wen Li]

Hi Rick
When it come to deal with time series, there is a very good free software called Gretl at http://gretl.sourceforge.net/. It's very flexible for modelling and forecasting, you might like to explore it.
Cheers,
Li 


-----Original Message-----
From: r-sig-ecology-bounces at r-project.org [mailto:r-sig-ecology-bounces at r-project.org] On Behalf Of Richard Boyce
Sent: Wednesday, 22 February 2012 1:47 AM
To: <r-sig-ecology at r-project.org>
Subject: [R-sig-eco] Time series analysis: moving average (MA) models with transfer functions

Colleagues,

I'm relatively new to time series analysis, and I've run into an issue that is driving me nuts.

I have several time series, i.e., daily sap flow amounts from several shrub species. These series often are best fit by MA(1) models. However, transfer functions using vapor pressure deficit, soil water content, or both often improve the model, and these transfer functions often have MA terms of their own.

This being a field study in a remote area, I also have missing data. So I'd also like to fill in the gaps using the fitted models with transfer functions.

However, the built-in functions in packages like TSA and forecast seem to have trouble with transfer functions with MA terms. And I cannot figure out how to hand-calculate the output that the model produce for the periods when I have data! MA models use previous error terms, but many of the sources I've consulted say you don't know what it is (so how does R do it?).

I've consulted Cryer and Chan (2008), hunted on the web, through archives at the R site, etc., and I've come up empty-handed. If anyone can point toward a source that that explains how I can take a fitted model of this sort to forecast ahead for short periods, I'd be most appreciative.

And by the way, if there is a better R-sig newsgroup to send this to, please let me know. I'm an ecologist and this is an ecological data set, but these models are used in many fields.

Thanks, Rick

================================
Richard L. Boyce, Ph.D.
Director, Environmental Science Program
Associate Professor
Department of Biological Sciences
Northern Kentucky University
Nunn Drive
Highland Heights, KY  41099  USA

859-572-1407 (tel.)
859-572-5639 (fax)
boycer at nku.edu<mailto:boycer at nku.edu>
http://www.nku.edu/~boycer/
=================================

"One of the advantages of being disorderly is that one is constantly making exciting discoveries." - A.A. Milne





	[[alternative HTML version deleted]]

_______________________________________________
R-sig-ecology mailing list
R-sig-ecology at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology
----------------------------------------------------------------------------------------------------------------------------------------------------------------------
This email is intended for the addressee(s) named and may contain confidential and/or privileged information. 
If you are not the intended recipient, please notify the sender and then delete it immediately.
Any views expressed in this email are those of the individual sender except where the sender expressly and with authority states them to be the views of the Office of Environment and Heritage, NSW Department of Premier and Cabinet.

PLEASE CONSIDER THE ENVIRONMENT BEFORE PRINTING THIS EMAIL