Read carefully.
I understand Svend's reference as drawing confidence intervals around
each observed value. I do not want that. I gives a graph that is
difficult to read as many hospitals I want observed value as plots
against a background with confidence limits around the reference value
at increasing numbers on the x-axis.
I will rephrase my question:
How can I draw confidence limits for a reference proportion
(proportion of deaths) at increasing number of operations, from 30 to
400? How can I combine such a graph with plots of observed mortality?
Greetings
Roland Andersson
2007/1/12, Svend Juul <[email protected]>:
> Roland Andersson wrote:
>
> I want to draw lines along the x-axis that show the limit
> of the 90 and 95% confidence interval for a mortality of 0.15%
> at increasing number of operations. I than will plot the
> results of each hospital. This will show the widening CI for
> the smaller hospitals and the distance from this CI line of each
> hospital in relation to the number of operations performed, I have
> used "by hospital: ci mortality, poisson" to calculate the CI for
> each hospital. I could plot these CI for each hospital to show the
> hospitals which has a lower CI above the mean, but I want rather the
> CI lines for the mean mortality and plot the hospitals as points.
> ---------------------------------------------------
>
> I am not sure about the soundness of putting confidence intervals
> around both the reference value (0.15%) and the observed values.
>
> Apart from that: I think you might benefit from -statsby-; see
> [D] statsby.
>
> Hope this helps
> Svend
>
> ________________________________________________________
>
> Svend Juul
> Institut for Folkesundhed, Afdeling for Epidemiologi
> (Institute of Public Health, Department of Epidemiology)
> Vennelyst Boulevard 6
> DK-8000 Aarhus C, Denmark
> Phone, work: +45 8942 6090
> Phone, home: +45 8693 7796
> Fax: +45 8613 1580
> E-mail: [email protected]
> _________________________________________________________
>
> *
> * 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/
>