[R] lme: subject-specific slopes.

[Kenneth Frost]

I think the random effects represent the subject adjustments to the population averages. You may have to do the addition yourself to get the subject specific slopes and intercepts. Someone will hopefully correct me if I'm wrong.

On 12/04/12, John Sorkin  wrote:
> 
> 
> 
> Ken,
> Thank you for your help. ranef(fitRIRT) does not give me what I expect. The subject-specific slopes, and subject-specific intercepts are not anywhere close to what I would expect them to be; the mean of the subject-specfic values should be close to those reported by 
> summary(fitRIRT) and they are not. As you will see by examining the material below, the subject-specific slopes are off by many order of magnitude. The intercepts are also far from the value reported in summary(fitRIRT). Do you have any thoughts?
> Thanks,
> John
> 
> 
> > fitRIRT <- lme(echogen~time,random=~ 1+time|subject,data=repeatdata,na.action=na.omit) > summary(fitRIRT) Linear mixed-effects model fit by REML Data: repeatdata AIC BIC logLik 495.097 507.2491 -241.5485 Random effects: Formula: ~1 + time | subject Structure: General positive-definite, Log-Cholesky parametrization StdDev Corr (Intercept) 1.917511e+01 (Intr) time 2.032276e-04 0 Residual 1.044601e+01 Fixed effects: echogen ~ time Value Std.Error DF t-value p-value (Intercept) 64.54864 4.258235 32 15.158543 0.0000 time 0.35795 0.227080 32 1.576307 0.1248 Correlation: (Intr) time -0.242 Standardized Within-Group Residuals: Min Q1 Med Q3 Max -1.61362755 -0.52710871 0.02948008 0.41793322 1.77340082 Number of Observations: 58 Number of Groups: 25 > ranef(fitRIRT) (Intercept) time 1 -3.278112 2.221016e-09 2 -35.400618 4.314995e-08 3 11.493110 -6.797543e-09 4 -16.209586 -7.070834e-08 5 3.585227 -2.389705e-08 6 1.614320 -1.967700e-09 7 8.346905 5.827094e-08 8 30.917812 -3.768584e-08 9 -0.394101 -9.158251e-09 10 4.437509 -4.057971e-08 11 31.956597 -2.126275e-08 12 41.567402 -4.853942e-08 13 -10.723993 1.307152e-08 14 -4.554837 5.551908e-09 15 -4.554501 4.815086e-08 16 13.296985 -3.743967e-08 17 -8.255439 1.733238e-08 18 -21.317239 2.203885e-08 19 -13.480159 2.194016e-08 20 -13.044766 2.269168e-08 21 11.639198 -1.418706e-08 22 -27.457388 -1.154099e-08 23 2.194001 -5.509119e-09 24 -3.992646 7.682188e-08 25 1.614320 -1.967700e-09
> 
> 
> 
> 
> 
> 
> 
> John David Sorkin M.D., Ph.D.
> Chief, Biostatistics and Informatics
> University of Maryland School of Medicine Division of Gerontology
> Baltimore VA Medical Center
> 10 North Greene Street
> GRECC (BT/18/GR)
> Baltimore, MD 21201-1524
> (Phone) 410-605-7119
> (Fax) 410-605-7913 (Please call phone number above prior to faxing)>>> Kenneth Frost <kfrost at wisc.edu> 12/4/2012 10:44 AM >>>
> I think this might be close to what you want. ranef(fitRIRT)
> 
> On 12/04/12, John Sorkin wrote:
> > I am running a random intercept random slope regression:
> > 
> > fitRIRT <- lme(echogen~time,random=~ 1+time|subject,data=repeatdata,na.action=na.omit)
> > summary(fitRIRT)
> > 
> > I would like to get the subject-specific slopes, i.e. the slope that the model computes for each subject. If I have 10-subjects I should have 10-slopes. I don't see the slope when I look at the items listed in 
> > names(summary(fitRIRT)
> > nor when I look at the items listed in 
> > names(fitRIRT)
> > 
> > Thanks 
> > John
> > 
> > 
> > 
> > 
> > 
> > 
> > John David Sorkin M.D., Ph.D.
> > Chief, Biostatistics and Informatics
> > University of Maryland School of Medicine Division of Gerontology
> > Baltimore VA Medical Center
> > 10 North Greene Street
> > GRECC (BT/18/GR)
> > Baltimore, MD 21201-1524
> > (Phone) 410-605-7119
> > (Fax) 410-605-7913 (Please call phone number above prior to faxing)
> > Confidentiality Statement:
> > This email message, including any attachments, is for the sole use of the intended recipient(s) and may contain confidential and privileged information. Any unauthorized use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message. 
> > 
> > 
> > ______________________________________________
> > R-help at r-project.org mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> 
> --
> Kenneth Frost
> Graduate Research Assistant - Dept. of Plant Pathology
> University of Wisconsin - Madison
> Lab: (608) 262-9914
> Mobile: (608) 556-9637
> kfrost at wisc.edu
> 
> 
> 
> 
> Confidentiality Statement: 
> 
> This email message, including any attachments, is for the sole use of the intended recipient(s) and may contain confidential and privileged information. Any unauthorized use, disclosure or distribution is prohibited. If you are not the intended recipient, please contact the sender by reply email and destroy all copies of the original message.

--
Kenneth Frost
Graduate Research Assistant - Dept. of Plant Pathology
University of Wisconsin - Madison
Lab: (608) 262-9914
Mobile: (608) 556-9637
kfrost at wisc.edu