Message-ID: <20030514110527.70e2c85d.fharrell@virginia.edu>
Date: 2003-05-14T15:05:27Z
From: Frank E Harrell Jr
Subject: building mean/median over subgroups
In-Reply-To: <p05200f00bae8001643f9@[128.40.218.142]>
On Wed, 14 May 2003 15:25:57 +0100
Frank Mattes <f.mattes at rfc.ucl.ac.uk> wrote:
> Dear all,
>
> I'm trying to solve the following problem, and hoping to get some
> advise here from the group
>
> I have a dataframe in which the same sample was measured more than
> once on the same day. I would reorganize the dataframe to get a
> single value (mean /median) for one day
>
> Patient Day Sample Test
> A 1 A 23
> A 1 A 36
> A 5 B 44
> A 5 B 23
> B 2 C 10
> B 2 C 5
>
>
> mean
>
> Patient Day Sample Test.mean
> A 1 A 29.5
> A 5 A 33.5
> B 2 C 7.5
>
>
> it would be great to get some help form the list.
>
> Yours
> Frank
> --
> Frank Mattes, MD e-mail: f.mattes at ucl.ac.uk
>
There are examples like this in Section 4.2 of http://hesweb1.med.virginia.edu/biostat/s/doc/splus.pdf
---
Frank E Harrell Jr Prof. of Biostatistics & Statistics
Div. of Biostatistics & Epidem. Dept. of Health Evaluation Sciences
U. Virginia School of Medicine http://hesweb1.med.virginia.edu/biostat