[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

From |
Tom Trikalinos <[email protected]> |

To |
[email protected] |

Subject |
Re: st:meta-analysis |

Date |
Fri, 3 Sep 2004 11:56:39 +0300 |

Generally speaking, if you want to check whether any factor(s) X1 (X2...) affect(s) Theta (ie the Effect Size), a meta-regression framework is probably warranted:

Try using _metareg_ and check the documentation.

. findit metareg

. metareg Theta X1 X2, wsse(seTheta)

Really advanced analysis would be based on Bayesian approaches and is relatively easily implemented in WinBUGS (free specialist software, try googling it). Lots of papers in Stat Med on Bayesian meta-analysis.

Hope this helps,

Tom

On Sep 3, 2004, at 11:11 AM, cui liwei wrote:

thanks Tom, but I still want to know if the sample size will affect the results.

you see, the "meta" doesn't take into account the "n".

input n theta se_theta

18 4.37 1.0740

18 3.13 1.5602

20 3.51 1.8622

21 3.34 1.9122

18 4.25 .60029

end

meta theta se_theta

From: Tom Trikalinos <[email protected]>

Reply-To: [email protected]

To: [email protected]

Subject: Re: st:meta-analysis

Date: Tue, 31 Aug 2004 11:59:48 +0300

I suppose you know what you're doing;

. findit metan

OR

.findit meta

yields useful routines. Use Coef values as the effect size (Theta) and the SE thereof as SE_theta.

Good luck

Tom

On Aug 31, 2004, at 11:44 AM, cui liwei wrote:

Dear all,

Here are the results of several regress,how to perform meta-analysis.

thanks!

Obs Coef. Std.Err. t P>|t|

18 4.37 1.0740 4.07 0.001

18 3.13 1.5602 2.01 0.062

.

.

18 4.25 .60029 7.08 0.000

Cui

_________________________________________________________________

~~{SkA*;z5DEsSQ=xPP=;Aw#,GkJ9SC~~} MSN Messenger: http://messenger.msn.com/cn

*

* 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/

* * 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/_________________________________________________________________ ~{SkA*;z5DEsSQ=xPP=;Aw#,GkJ9SC~} MSN Messenger: http://messenger.msn.com/cn * * 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/

* * 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/

**References**:**Re: st:meta-analysis***From:*"cui liwei" <[email protected]>

- Prev by Date:
**RE: st: Technical problem with STATA** - Next by Date:
**st: Re: Logit and percentage of correct classification** - Previous by thread:
**Re: st:meta-analysis** - Next by thread:
**Re: st:meta-analysis** - Index(es):

© Copyright 1996–2024 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |