From: Milton Cezar <miltinho_astronauta_at_yahoo.com.br>

Date: Wed 31 May 2006 - 06:14:06 EST

From: r-help-bounces@stat.math.ethz.ch On Behalf Of Milton Cezar Sent: Tuesday, May 30, 2006 11:42 AM

R-help@stat.math.ethz.ch mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Wed May 31 06:28:19 2006

Date: Wed 31 May 2006 - 06:14:06 EST

Data: Tue, 30 May 2006 16:08:26 -0300 (ART)
De: Milton Cezar <miltinho_astronauta@yahoo.com.br>
Assunto: R: Piecewise (broken stick) models in R && Stats for groups
Para: r-help-bounces@stat.math.ethz.ch

Chris Barker and everyone

Thanks for your fast replay.

Regarding the descreptive Stats, I can compute it for the full dataset, but I can´t comput it for groups of that.
I used mean ( Rainfall [year==1980] ) without problem. But how can I get the mean Rainfall for Year==1980 AND Site=1; Year=1980 AND Site=2 etc.

Regarding my question for Pieacewise Regression model It can really be done with liner models functions. In fact, the results are a set of models that work bether in different range of an X variable (for X varying 0 to 0.15 use model_1; for 0.16 to 0.46 use model_2... for X>0,47 use model_3 etc.

Sorry for my broken english,

Regards a lot,

Miltinho

From: Barker, Chris [SCIUS]

To: 'Milton Cezar'

Sent: Tuesday, May 30, 2006 3:47 PM

Subject: RE: [R] Piecewise (broken stick) models in R
You can get descriptive statistics with mean(), var() or summary().
AS to broken stick, I can only speculate that's a variation on a regression. You may need to be more specific in your questions to the list, as I suspect its something easily done in the linear models functions.

Chris Barker

Associate Director, Biostatistics

Scios Inc.

6500 Paseo Padre Parkway

Fremont, CA 94555

Tel 510 248 2439

Fax 510 248 2451

From: r-help-bounces@stat.math.ethz.ch On Behalf Of Milton Cezar Sent: Tuesday, May 30, 2006 11:42 AM

To: r-help@stat.math.ethz.ch Subject: [R] Piecewise (broken stick) models in R

<< File: ATT17883177.txt >> Hi there, I´m a newbie in R and I´m looking for some advice how to teste Piecewise (Broken Stick) models.

I´have another simple question: how can I compute descriptive statistics for data grouped for two or more variables? See below, please.

Year Site Repetition rainfall

1980 1 1 ... 1980 1 2 ... 1980 1 3 ... 1980 2 1 ... 1980 2 2 ... 1980 2 3 ... 1990 1 1 ... 1990 1 2 ... 1990 1 3 ... 1990 2 1 ... 1990 2 2 ... 1990 2 3 ...

I´d like to compute the mean rainfall for each YEAR * SITE combination.

Kind regards,

Miltinho

[[alternative HTML version deleted]]

R-help@stat.math.ethz.ch mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Wed May 31 06:28:19 2006

Archive maintained by Robert King, hosted by
the discipline of
statistics at the
University of Newcastle,
Australia.

Archive generated by hypermail 2.1.8, at Wed 31 May 2006 - 08:13:50 EST.

*
Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help.
Please read the posting
guide before posting to the list.
*