Message-ID: <48CFE7AA.30101@biostat.ku.dk>
Date: 2008-09-16T17:06:50Z
From: Peter Dalgaard
Subject: creating baseline variable from a longitudinal sequence
In-Reply-To: <888120.85612.qm@web63105.mail.re1.yahoo.com>
john james wrote:
> Dear R-help mailing list,
> ?
> Kindly help me out with this problem:
> ?
> I have a dataset that is in the format below,
> ID? time? Y? Age
> 1? 0???? 195? 23.1
> 1? 2??? 204? 23.3
> 1? 4?? 202??? 23.5
> 2? 0? 170??? 22.0
> 2? 3?? 234?? 22.2
> 3? 0? 208?? 24.4
> 3? 2? 194? 24 .7
> 3? 3?? 204? 24.9
> ?
> I wish to remove all the measurements at time point 0 and convert?them to a baseline variable as follows;
> ?
> ?ID? time? Y? Age? baseline
> 1? 2??? 204? 23.3?? 195
> 1? 4?? 202??? 23.5?? 195
> 2? 3?? 234?? 22.2??? 170
> 3? 2? 194? 24 .7???? 208
> 3? 3?? 204? 24.9???? 208
>
Something in your mail path (or mine) is inserting funny characters in
your text, making it a bit hard to use the data for testing...
Anyways, I'd split the data frame into the baseline values and the rest
using subset() or maybe split(), rename the baseline variable(s) and
then stick things together with merge()
--
O__ ---- Peter Dalgaard ?ster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907