Adding -ciopts(horizontal)- is the implied syntax
and produces a graph. However, it is not the
graph you want, as the -horizontal- option
affects only the display of the point estimates,
while the intervals are plotted as before.
The solutions appear to be:
1. do-it-yourself with -twoway-.
2. Roger Newson's -eclplot-.
Both depend on creating a so-called resultsset
first.
3. Wait for StataCorp to fix this in Stata 9.
It's not impossible that they might just trap
this as a complication too far. Also,
that depends on your upgrading as well as their
action.
Nick
[email protected]
Jonathan Kaplan
> I would like to produce a plot with a horizontal tabodds ciplot
>
> I'm trying to summarize odds of survival from several trials, in which
> pop1 is total population, pop0 numbers surviving and salvage=type of
> salvage treatment
>
> pop1 pop0 salvage
> 9 5 2
> 27 11 2
> 13 9 3
> 4 3 3
> 9 6 1
> 5 4 1
>
> tabodds pop0 salvage, binomial (pop1) ciplot recast(scatter) is the
> graph- however the horizontal option does not seem to work for ciplot
> ?
*
* 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/
