Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# Re: st: RE: sensitivity and specificity with CI's

 From Phil Clayton <[email protected]> To [email protected] Subject Re: st: RE: sensitivity and specificity with CI's Date Sat, 16 Jun 2012 20:03:22 +1000

```Precise literature references please. See section 3.4 of the Statalist FAQ.

Watkins C, Daniels L, Jack C, Dickinson H, van Den Broek M. Accuracy of a single question in screening for depression in a cohort of patients after stroke: comparative study. BMJ. 2001 Nov 17;323(7322):1159.

I can't see how they've calculated the CIs. I would not lose sleep over it - if you look at the pre-publication history they didn't even include CIs originally, and they haven't bothered to describe their methodology. If you're desperate to find out you could contact the corresponding author.

The prevalence is just the proportion of people with the disease. In this case they state that 43 of 79 patients (54%) had depression. This is also given in the -diagt- output.

Phil

On 16/06/2012, at 11:08 AM, Fran Baker wrote:

> Thanks that's great Paul.
>
> I am looking at a paper by Watkins et al (2001) and trying to match their calculations.
>
> using       diagti 37 6 8 28  goes well except for the 95%CI's of sensitivity and specificity
>
> The paper gives 95%CI's as
> sp = 78%   (65 to 91%)
> sn = 86% (75 to 97%)
> Have you any idea how these may have been calculated - tried all cii options
>
> Also the prevalence is given as 54%.  Do you know how this is found?
>
> Cheers
> Fran
>
>>>> "Visintainer, Paul" <[email protected]> 15/06/2012 11:41 pm >>>
> You can use -diagt-, which provides CIs.  You can also compute the confidence intervals using -ci-, since sensitivity and specificity are proportions
>
> -Paul
>
> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On Behalf Of Fran Baker
> Sent: Friday, June 15, 2012 9:14 AM
> To: [email protected]
> Subject: st: sensitivity and specificity with CI's
>
> Hi
>
> Is there a command for calculating sensitivity and specificity with CI's?  Have looked and found some but not sure of the quality and there don't appear to be CI's.
>
> Thanks
> Fran
>
> *
> *   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/
>
> ----------------------------------------------------------------------
> Please view our annual report at http://baystatehealth.org/annualreport
>
>
> CONFIDENTIALITY NOTICE: This e-mail communication and any attachments may contain confidential and privileged information for the use of the designated recipients named above. If you are not the intended recipient, you are hereby notified that you have received this communication in error and that any review, disclosure, dissemination, distribution or copying of it or its contents is prohibited. If you have received this communication in error, please reply to the sender immediately or by telephone at 413-794-0000 and destroy all copies of this communication and any attachments. For further information regarding Baystate Health's privacy policy, please visit our Internet site at http://baystatehealth.org.
>
> *
> *   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/
>
> *
> *   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/

*
*   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/
```