Line for the server...

Truth be told, A.S.J. did say in the subject line that he is now conducting

his estimations in Stata 10, and I overlooked that in my reply. But, as Nick

has said, the question remains shrouded in mystery...

HTH

Martin

-----Original Message-----

From:

[hidden email]
[mailto:

[hidden email]] On Behalf Of Nick Cox

Sent: Tuesday, December 02, 2008 5:32 PM

To:

[hidden email]
Subject: st: RE: RE: ret list of STATA10

To strengthen Martin's point:

This question is at best very difficult to answer without knowing

1. Which version of -metan- you are using. Show the results of -which

metan-.

2. What you typed, precisely.

3. What you mean by "usually provided by Stata 9.2". I can't see that

has any meaning in itself.

What you are seeing are basically what might be expected after a

raphics command. I can't say which.

Nick

[hidden email]
Martin Weiss

What has changed? Have you switched to Stata 10 or updated -metan- or

both?

Try to formulate your question in terms of the examples in -h metan-...

Mendis, A.S.J.

I have run a meta-analysis using METAN command on odds ration scale, and

the

used RET LIST to see the saved results. The output I got is as below.

It does not provide the pooled estimate of the effect size, tau squared,

SE

of log odds ratio, ect. which usually provided by STATA 9.2

Thanks

scalars:

r(ymin) = 0

r(ymax) = 8

r(xmin) = .0469176173210144

r(xmax) = 1046.383911132813

r(ay) = -2339.5

r(by) = 19771

r(ax) = 2544.230488395218

r(bx) = 13254.72217268045

macros:

r(dbox) : "1055,5471,19771,30945,443,213,0"

r(gbox) : "0,0,22376,32000,923,444,0"

This output is different to the one that I usually see in Intercooled

STATA

9.2

*

* 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/