s-news
[Top] [All Lists]

setting random terms in lme

To: "SPLUS_NEWS" <s-news@lists.biostat.wustl.edu>
Subject: setting random terms in lme
From: "Bill Shipley" <bill.shipley@usherbrooke.ca>
Date: Thu, 27 Jan 2005 11:04:26 -0500
Importance: Normal

Hello.  I am fitting a simple linear model to data with a 3-level hierarchy (species, plants within species, times within individuals).  The model is:

 

Random effects:

 Formula:  ~ 1 + time | Sp

 Structure: General positive-definite

                StdDev   Corr

(Intercept) 1.05723143 (Inter

       time 0.03824994 -0.53

 

 Formula:  ~ 1 + time | plante %in% Sp

 Structure: General positive-definite

                StdDev   Corr

(Intercept) 0.18103949 (Inter

       time 0.01453066 1    

   Residual 0.48031388      

 

Fixed effects: log(FM) ~ time

                Value Std.Error  DF   t-value p-value

(Intercept) -4.213142 0.1933546 823 -21.78972  <.0001

       time  0.250802 0.0072350 823  34.66499  <.0001

 Correlation:

     (Intr)

time -0.537

 

QUESTION:  I note that the correlation between the intercepts and slopes (time) for plants within species is 1.0.  This indicates (I think) that I should not allow both to randomly vary at this level.  However, the equivalent correlation at the level of species is -0.53 and I do what both the slopes and intercepts to vary at this species level.  How can I specify this?  Specifically, that both slopes and intercepts can vary at one level but only one of the two can vary at a lower level?

 

Thanks for any help.

 

Bill Shipley

Subject Matter Editor, Ecology

North American Editor, Annals of Botany

Département de biologie, Université de Sherbrooke,

Sherbrooke (Québec) J1K 2R1 CANADA

Bill.Shipley@USherbrooke.ca

http://callisto.si.usherb.ca:8080/bshipley/

 

<Prev in Thread] Current Thread [Next in Thread>