 |
 |
Thank you very much indeed!! Those are very good hints. -- Vicent > -----Mensaje original----- > De: email list for Radical Statistics > [mailto:[log in to unmask]] En nombre de Bland, M. > Enviado el: martes, 28 de agosto de 2007 9:54 > Para: [log in to unmask] > Asunto: Re: [OFF TOPIC] Confidence Interval for proportion > > You can download a free DOS program from my website. Robert > Newcombe has lots of stuff, including Excel spreadsheets, to > do a variety of methods: > > http://www.cardiff.ac.uk/medicine/epidemiology_statistics/research/statistic s/newcombe/proportions > > Martin > > Vicent Giner Bosch wrote: > > First of all, sorry for posting an 'off topic' and very > easy question, > > but I needed it. > > > > If I want to compute a 95% confidence interval (two-tailed) for an > > unknown proportion "p" within a population, I know the equation for > > it, if the sample size "n" is high enough to assume > normality -that is: > > > > CI95%(p) = estimated_p +/- z(0.025) * SQRT( > > estimated_p*(1-estimated_p) / n ) > > > > isn't it? > > > > But, what if "n" is small (between 10 and 20, say), and we can't or > > don't want to assume normality? I know I should use binomial > > distribution, but I don't know exactly how. > > > > Thank you in advance for your contributions. > > > > Yours, > > > > > > -- > > Vicent > > > > -- > *************************************************** > J. Martin Bland > Prof. of Health Statistics > Dept. of Health Sciences > Seebohm Rowntree Building Area 2 > University of York > Heslington > York YO10 5DD > > Email: [log in to unmask] > Phone: 01904 321334 > Fax: 01904 321382 > Web site: http://martinbland.co.uk/ ****************************************************** Please note that if you press the 'Reply' button your message will go only to the sender of this message. If you want to reply to the whole list, use your mailer's 'Reply-to-All' button to send your message automatically to [log in to unmask] Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk. *******************************************************