That was just a snippet of my data. I have 632 persons and 6308 observations.
On 8/29/05, P Rudd <[log in to unmask]> wrote:
> Data set is a bit small to do a test!
>
> ----- Original Message -----
> From: "Raphael Fraser" <[log in to unmask]>
> To: <[log in to unmask]>
> Sent: Monday, August 29, 2005 10:31 PM
> Subject: QUERY: Prevalence
>
>
> Dear All,
>
> If one is faced with a longitudinal data set as given below, where the
> variable test is the result of a blood test for protein (pos=protein;
> neg=no protein). Can one calculate the prevalence of protein in the
> blood? Is it sensible?
>
> id test
> 1 pos
> 1 pos
> 1 pos
> 1 neg
> 2 pos
> 2 neg
> 2 neg
> 2 pos
> 2 neg
>
> Regards,
> Raphael
>
--
=============================
Raphael A. Fraser, MSc
Assistant Lecturer in Biostatistics
Sickle Cell Unit
Tropical Medicine Research Institute
Faculty of Medical Sciences
University of the West Indies
Kingston
Jamaica
Tel: (876) 927-2471; 410-4699
Fax: (876) 927-2984
e-mail: [log in to unmask]
|