Probability estimates in lme

["Roberts, J. Kyle" <jkrobert@bcm.tmc.edu>]

Dear All,

 

I want to extract the Gaussian probability estimates from lme for use in a statistic that I am developing.  Any ideas how to get this?  What I am looking for is the p(Yij) for a 2-level model given that:

 

 

 

I am using the Roberts(2004) data which I will put up on my website in a couple of minutes:

http://www.hlm-online.com/datasets/

 

Here's the code I have generated thus far using S-PLUS 6.2 on Windows XP Professional:

> lme.out<-lme(SCIENCE~URBAN, data="" random = ~URBAN|GROUP)
> summary(lme.out)
Linear mixed-effects model fit by REML
 Data: example.data
       AIC      BIC    logLik
  424.1713 442.5469 -206.0857

 

Random effects:
 Formula:  ~ URBAN | GROUP
 Structure: General positive-definite
                StdDev   Corr
(Intercept) 10.6584842 (Inter
      URBAN  0.5019958 -0.625
   Residual  0.5202538      

 

Fixed effects: SCIENCE ~ URBAN
                Value Std.Error  DF   t-value p-value
(Intercept)  22.39124  2.717018 143  8.241111  <.0001
      URBAN  -0.86701  0.129811 143 -6.678989  <.0001

 

Standardized Within-Group Residuals:
       Min         Q1         Med        Q3      Max
 -2.376494 -0.7914869 0.007393824 0.6221058 2.169879

 

Number of Observations: 160
Number of Groups: 16

 

Thanks,

Kyle

 

***************************************

J. Kyle Roberts, Ph.D.

Baylor College of Medicine

Center for Educational Outreach

One Baylor Plaza, MS:  BCM411

Houston, TX   77030-3411

713-798-6672 - 713-798-8201 Fax

jkrobert@bcm.edu

***************************************