[R] Multilevel Modeling using R

Stas Kolenikov skolenik at gmail.com
Tue Mar 17 21:22:07 CET 2009

In most biometric applications, those variances are treated as
nuisance parameters. They only need to be controlled for, while the
main purpose is to get the right point estimates and standard errors
for the fixed effects. In social science multilevel modeling (of which
education is probably the heaviest user), the variances usually mean
something, so there is interest in conducting inference on them (as
you probably want to do). As noted by Harold Doran, whatever you do
with these random effects is quite sensitive to their distributions.
Getting the standard errors on those variances usually comes from
assuming a particular model such as the normal one.

What you do looks more like ANOVA to me. So you can use aov() to get
some F-statistics on your within- and between-school variability.

On 3/17/09, WONG, Ka Yau <kayau at ied.edu.hk> wrote:
> Dear experts,
>           I use R to conduct multilevel modeling. However, I have a problem about the interpretation of random effect. Unlike the variables in fixed effects, the variables in random effects have not shown the standard error (s.e.) and p-value, so I don't know whether they are significant or not? I want to obtain these figures to make the decision. Thank you for your great help!
>  Below is the syntax and output of my program:
>  library(nlme)
>  dataset <- read.csv("d:/dataset.csv")
>  lme11 <- lme(Overall~1, random=~1|School, method="ML", data=dataset)
>  summary(lme11)
>  Linear mixed-effects model fit by maximum likelihood
>  Data: dataset
>        AIC      BIC   logLik
>   12637.06 12656.27 -6315.53
>  Random effects:
>  Formula: ~1 | School
>                (Intercept)  Residual
>  StdDev:   0.2912031 0.9894488        (<-- No s.e. & p-value)
>  Fixed effects: Overall ~ 1
>                     Value       Std.Error       DF    t-value     p-value
>  (Intercept) 0.7755495 0.06758038 4444 11.47596       0            (<-- Have s.e. & p-value)
>  Standardized Within-Group Residuals:
>     Min          Q1           Med           Q3            Max
>  -3.797466473 -0.661750231 -0.007874993  0.652625939  3.549169733
>  Number of Observations: 4464
>  Number of Groups: 20
>  Best Regards,
>  Tommy
>  Research Assistant of HKIEd
>         [[alternative HTML version deleted]]
>  ______________________________________________
>  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.

Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

More information about the R-help mailing list