Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Negative Predictive Value
From
Ronan Conroy <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: Negative Predictive Value
Date
Mon, 5 Sep 2011 10:27:00 +0100
On 2011 MFómh 4, at 18:17, Jayson Trinchera wrote:
> How do you compute for the minimum required sample size for
> determining the negative predictive values of two diagnostic methods
> with a binary outcome/result (either positive or negative)?
The negative predictive value is a function of the prevalence, so the sample size calculation will critically involve prevalence.
A more general approach is based on clinical likelihood ratios, which are independent of prevalence. A useful reference is
http://www.ncbi.nlm.nih.gov/pubmed/1941027
J Clin Epidemiol. 1991;44(8):763-70.
Likelihood ratios with confidence: sample size estimation for diagnostic test studies.
Simel DL, Samsa GP, Matchar DB.
You might note also that there is a user-written command -fagan- (by Ben Adarkwa Dwamena)which allows you to convert likelihood ratios into post-test probabilities at any given prevalence.
Ronán Conroy
[email protected]
Associate Professor
Division of Population Health Sciences
Royal College of Surgeons in Ireland
Beaux Lane House
Dublin 2
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/