Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: Subject: st: decimal points in funnel plot


From   Vasan Kandaswamy <vasan.kandaswamy@ki.se>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   RE: Subject: st: decimal points in funnel plot
Date   Thu, 30 Aug 2012 12:17:27 +0000

Sorry Nick and Ross,
This is the script I have used
metan whr_beta whr_se, lcols(study) by (area_qn) xlabel(-0.015,-0.010,-0.005,0,0.005,0.010,0.015)

whr- waist hip ratio
beta-estimate
se-standard error
study (n=8)
area_qn ( sub grouped as migration and indigenous population)

Best, 
Senthil 



________________________________________
From: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu] on behalf of Nick Cox [njcoxstata@gmail.com]
Sent: Thursday, August 30, 2012 2:04 PM
To: statalist@hsphsun2.harvard.edu
Subject: Re: Subject: st: decimal points in funnel plot

Ross guessed that you were using -metan- (SJ/SSC). He was obliged to
guess because you did not give precise details of the code you used.
We are still lacking any precise details of the code you used.

Nick

On Thu, Aug 30, 2012 at 12:56 PM, Sentil Vasan Kandaswamy wrote:

> Thank you very much. I am sorry, I was actually referring to Forest plots. The outcome of interest is waist-hip ratio, which makes it difficult or rather not possible to change the scale of estimates.
> If you have any further suggestions of this, it would be of great help.

Ross.Harris@hpa.org.uk]

> I am wondering if you refer to forest plots rather than funnel plots, as
> the funnel plot does not display study estimates. If you mean forest
> plots, and are using metan, then you are right: unfortunately it is not
> possible to change the decimal places. This is because most applications
> use risk ratios of some sort, which are generally adequately displayed
> to 2dp. This is something on the wishlist to be changed in future.
>
> If your estimates really are so small, then perhaps they are
> non-standardised mean differences. In which case, I would suggest
> changing the scale of your estimates - e.g., grams to kilograms, 1000s
> of whatever measure you are using, etc. Similarly, if you are analysing
> some non-standard measure, such as rates, then change the scale of
> these. Hopefully this is something that will be updated in future, but
> this will have to do for now.

Vasan Kandaswamy <vasan.kandaswamy@ki.se>

> I am doing a meta-analysis and would like to seek help on editing funnel
> plots in STATA.
>
> For a particular trait that I am interested in, the effect size and
> 95%CI are in the range of 0.001-0.0004. The funnel plot shows only upto
> two decimal points ( which makes it appear 0.00 for all studies in the
> analysis).  I would much appreciate if someone tells me, how this could
> be edit  to 3-4 decimal points.
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index