Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: count number of cases rather than observations


From   "David Winter" <[email protected]>
To   <[email protected]>
Subject   RE: st: count number of cases rather than observations
Date   Mon, 28 Nov 2005 17:23:29 -0000

Thanks Eric - this was very helpful

***********************************************************
Mr David L. Winter, HNC
IT Manager (BCCSS Study)
Department of Public Health & Epidemiology
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK
tel: +44 (0)121 4146766
fax: +44 (0)121 4147923
***********************************************************


-----Original Message-----
From: [email protected]
[mailto:[email protected]]On Behalf Of Eric Cahuzac
Sent: 25 November 2005 08:30
To: [email protected]
Subject: Re: st: count number of cases rather than observations


David,
try in two steps:

preserve
bysort id-number riskint: keep if _n==1
bysort riskint: count
restore

the count instruction give
------------------------------------
-> riskint = 0-9
    5
------------------------------------
-> riskint = 10-19
    2

not so pretty but working...
Eric


David Winter a �crit :

>Hello,
>
>I have some survival data and I want to identify the number of cases
>that contribute person-time at risk. I also want to split the case by
>age. I -stset- and -stsplit by age (entry to exit) and the by risk
>interval:
>
>stset var1 enter(time var2) fail(censor-var) id(id-number)
>stsplit ageband at (.....)
>
>stset var3 enter(time var4) fail(censor-var) id(id-number)
>stsplit riskint at (....)
>
>for 5 cases I might have the data split as follows:
>
>id-number       ageband        riskint
>---------       -------        -------
>1               0-4            0-9
>1		    5-9		 0-9
>1               10-14          10-19
>2               0-4            0-9
>2               5-9            0-9
>3               0-4            0-9
>4               0-4            0-9
>5               0-4            0-9
>5               5-9            0-9
>5               10-14          10-19
>
>If I group by 'riskint' I would get the following result based on
>observations
>
>Riskint	no of obs (contribute person-time at risk)
>-------     ---------
>0-9             8
>10-19           2
>
>But what I want to identify and record is the no. of cases contributing
>person-time at risk in each risk interval.
>
>Riskint      no of cases
>-------      -----------
>0-9             5
>10-19           2
>
>There must be an easy way to do this?
>
>Best wishes,
>Dave             
>
>****************************************************
>Mr David L. Winter, HNC
>I.T. Manager (BCCSS Study)
>Department of Public Health & Epidemiology
>Room 105, Public Health Building
>University of Birmingham
>Edgbaston
>Birmingham
>B15 2TT
>UK
>tel.: +44 (0)121 414 6766
>fax.: +44 (0)121 414 7923
>****************************************************
>
>
>*
>*   For searches and help try:
>*   http://www.stata.com/support/faqs/res/findit.html
>*   http://www.stata.com/support/statalist/faq
>*   http://www.ats.ucla.edu/stat/stata/
>
>
>  
>


-- 
______________________________

Eric Cahuzac
Institut National de la Recherche Agronomique (INRA)
Station d'Economie et Sociologie Rurale (ESR)
Chemin de Borde-Rouge - Auzeville
BP 52627, 31326 CASTANET-TOLOSAN CEDEX
Tel. 05.61.28.53.41 (direct)
     05.61.28.53.49 (secr�tariat)
Fax. 05.61.28.53.72
e-mail  [email protected]
http://www.toulouse.inra.fr/esr

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index