[R-sig-ME] examples in Raudenbush and Bryk

Douglas Bates bates at stat.wisc.edu
Wed Aug 5 01:27:59 CEST 2009

On Tue, Aug 4, 2009 at 3:23 PM, Tobias Verbeke<tobias.verbeke at gmail.com> wrote:
> Douglas Bates wrote:
>> On Tue, Aug 4, 2009 at 9:24 AM, Juliet Hannah<juliet.hannah at gmail.com>
>> wrote:
>>> Hi List,
>>> Does anyone know if nlme or lme4 code is available for the examples in
>>> RB 2002 (specifically
>>> Chapter 8, but other chapters also if available).
>> It would not be difficult to code up those examples in lme or lmer if
>> we could get access to the data sets.  Are the data sets available,
>> perhaps with the HLM software?
> I found this:
> ftp://ftp.lisrel.com/hlm/unix/hlm5exs.tar.Z
> According to the readme
> ftp://ftp.lisrel.com/hlm/unix/readme
> the datasets accompany the HLM5 manual,
> but some (HSB1 from appendixa/ e.g.) are
> reported elsewhere as being analyzed in
> Raudenbush and Bryk (2002). I don't have
> a copy so cannot help in identifying the
> data from Chapter 8 (if present).

Thanks for checking on that, Tobias.  As far as I can see that tar
file contains the data from the High School and Beyond study (HSB) in
appendix a, the EG data set in appendix b and the THAI data set in
appendix c.  These are the ones available in an ASCII format.  Other
data sets are only available in a SAS format for a VM/CMS machine
(interesting concept of "portable data format").

One can convert these to R data sets.  The EG data are already
available as egsingle in the mlmRev package and a truncated version of
the HSB data are available as Hsb82 in the same package.  The THAI
data can be converted as shown in the enclosed.

> HTH,
> Tobias

More information about the R-sig-mixed-models mailing list