I am having difficulty finding the covariance for the random effects in a mixed effects model. I fit this model: fm1 <- lmer(fpg ~ 1 + time + (1|ID) + (0+time|ID),fpg_lme) and want to find the covariance between the time and intercept random effects. I tried using VarCorr (see below) but it does not give the covariance or correlation between the random effects. Am I doing something wrong? Thanks, Kurt> summary(fm1)Linear mixed model fit by REML Formula: fpg ~ 1 + time + (1 | ID) + (0 + time | ID) Data: fpg_lme AIC BIC logLik deviance REMLdev 1499289 1499339 -749639 1499259 1499279 Random effects: Groups Name Variance Std.Dev. ID (Intercept) 1.0396e+03 32.2435465 ID time 1.2199e-05 0.0034926 Residual 1.1241e+02 10.6025764 Number of obs: 174042, groups: ID, 55526 Fixed effects: Estimate Std. Error t value (Intercept) 1.108e+02 1.421e-01 779.9 time 2.106e-03 6.678e-05 31.5 Correlation of Fixed Effects: (Intr) time -0.163> VarCorr(fm1)$ID (Intercept) (Intercept) 1039.646 attr(,"stddev") (Intercept) 32.24355 attr(,"correlation") (Intercept) (Intercept) 1 $ID time time 1.219857e-05 attr(,"stddev") time 0.003492645 attr(,"correlation") time time 1 attr(,"sc") sigmaREML 10.60258
Viechtbauer Wolfgang (STAT)
2009-Nov-12 07:44 UTC
[R] Finding covariance in a lmer mixed effects model
The way you have specified the model implies that the covariance is 0. If you actually want to estimate the covariance, you need to use: fm1 <- lmer(fpg ~ 1 + time + (time|ID), fpg_lme) Best, -- Wolfgang Viechtbauer http://www.wvbauer.com/ Department of Methodology and Statistics Tel: +31 (0)43 388-2277 School for Public Health and Primary Care Office Location: Maastricht University, P.O. Box 616 Room B2.01 (second floor) 6200 MD Maastricht, The Netherlands Debyeplein 1 (Randwyck) ----Original Message---- From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-project.org] On Behalf Of Kurt Smith Sent: Thursday, November 12, 2009 05:56 To: r-help at r-project.org Subject: [R] Finding covariance in a lmer mixed effects model> I am having difficulty finding the covariance for the random effects > in a mixed effects model. I fit this model: fm1 <- lmer(fpg ~ 1 + > time + (1|ID) + (0+time|ID),fpg_lme) > > and want to find the covariance between the time and intercept random > effects. > > I tried using VarCorr (see below) but it does not give the covariance > or correlation between the random effects. Am I doing something > wrong? > > Thanks, > Kurt > >> summary(fm1) > Linear mixed model fit by REML > Formula: fpg ~ 1 + time + (1 | ID) + (0 + time | ID) > Data: fpg_lme > AIC BIC logLik deviance REMLdev > 1499289 1499339 -749639 1499259 1499279 > Random effects: > Groups Name Variance Std.Dev. > ID (Intercept) 1.0396e+03 32.2435465 > ID time 1.2199e-05 0.0034926 > Residual 1.1241e+02 10.6025764 > Number of obs: 174042, groups: ID, 55526 > > Fixed effects: > Estimate Std. Error t value > (Intercept) 1.108e+02 1.421e-01 779.9 > time 2.106e-03 6.678e-05 31.5 > > Correlation of Fixed Effects: > (Intr) > time -0.163 > > >> VarCorr(fm1) > $ID > (Intercept) > (Intercept) 1039.646 > attr(,"stddev") > (Intercept) > 32.24355 > attr(,"correlation") > (Intercept) > (Intercept) 1 > > $ID > time > time 1.219857e-05 > attr(,"stddev") > time > 0.003492645 > attr(,"correlation") > time > time 1 > > attr(,"sc") > sigmaREML > 10.60258 > > ______________________________________________ > 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.