Statalist


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

R: st: R: Pooled effects for continuous data


From   "Carlo Lazzaro" <[email protected]>
To   <[email protected]>
Subject   R: st: R: Pooled effects for continuous data
Date   Thu, 13 Nov 2008 09:57:21 +0100

Dear Louise,
apart from reminding one of the already mentioned Stata routine (please,
type - help metan -) as far as costs are concerned, I would strongly
recommend you to take a look at Glick HA, Doshi JA, Sonnad SS, Polsky D.
Economic Evaluation in Clinical Trials. Oxford: Oxford University Press,
2007: 207-228. 

Another thought about a quick (and probably too much) dirty way for dealing
with your issue might be to weight your data for the number of patients
enrolled in each trials.

Sorry I cannot be more helpful.
I do hope that Someone else on the list will chime in with a smarter
insight.

Kind Regards,
Carlo

-----Messaggio originale-----
Da: [email protected]
[mailto:[email protected]] Per conto di Louisa Lam
Inviato: giovedì 13 novembre 2008 6.24
A: [email protected]
Oggetto: Re: st: R: Pooled effects for continuous data

Dear Carlo,

Thanks for the information. It is very helpful to know that Stata can be 
used for meta-analysis. However, after reading through all the 
functions, I still couldn't find anything to caculate the pooled effect 
for 'medians and IQR' and the pooled effects for 'different in cost and 
its 95% CI'.

For example for hospital length of stay(unit in days):
Study 1 median: 45      IQR: 36, 50
Study 2 median: 32      IQR: 28, 40
Study 3 median: 17      IQR: 12. 22
Study 4 median: 28     IQR: 23, 38

Is there anyway to caculate an effect estimate and a 95% CI of the above 
4 studies?

Louisa


Carlo Lazzaro wrote:
> Dear Louisa,
> The following ones may of interest fot your research purposes.
>
> Kind Regards,
>
> Carlo (A Stata 9.2/SE user)
>
>
----------------------------------------------------------------------------
> ------------------------------------------------
> search for metan
> (manual:  [R] search)
>
----------------------------------------------------------------------------
> ------------------------------------------------
>
>         Keywords:  metan
>           Search:  (1) Official help files, FAQs, Examples, SJs, and STBs
>
>
> Search of official help files, FAQs, Examples, SJs, and STBs
>
> FAQ     . . . . . . . . . . . User-written packages for meta-analysis in
> Stata
>         . . . . . . . . . .  J. Sterne, R. Harris, R. Harbord, and T.
> Steichen
>         1/07    What meta-analysis features are available in
>                 Stata?
>                 http://www.stata.com/support/faqs/stat/meta.html
>
> SJ-4-2  pr0012  . . . . . . . . Submenu and dialogs for meta-analysis
> commands
>         (help meta_dialog if installed) . . . . . . . . . . . . T. J.
> Steichen
>         Q2/04   SJ 4(2):124--126
>         provides Stata dialog boxes and commands to create a submenu
>         for publicly available meta-analysis commands
>
> SJ-4-2  st0061  . . . . . . . . . . . . . . . .  Funnel plots in
> meta-analysis
>         (help metafunnel if installed)  . .  J. A. C. Sterne and R. M.
> Harbord
>         Q2/04   SJ 4(2):127--141
>         discusses funnel plots, possible causes of asymmetry, and
>         the metafunnel command
>
> STB-45  sbe24.1 . . . . . . . . . . . . . . . . . .  Correction to funnel
> plot
>         (help funnel if installed)  . . . M. Bradburn, J. Deeks, and D.
> Altman
>         9/98    p.21; STB Reprints Vol 8, p.100
>
> STB-44  sbe24 . . . . . . . . .  metan -- an alternative meta-analysis
> command
>         (help metan if installed) . . . . . . . . .  Bradburn, Deeks, &
> Altman
>         7/98    pp.4--15; STB Reprints Vol 8, pp.86--100
>         meta-analysis command for studies with two groups
>
> (end of search)
> -----Messaggio originale-----
> Da: [email protected]
> [mailto:[email protected]] Per conto di Louisa Lam
> Inviato: martedì 11 novembre 2008 5.07
> A: Statistic Help
> Oggetto: st: Pooled effects for continuous data
>
> I am doing a meta-analysis which I need to calculate the pooled effects 
> for continuous data from a group of studies.
> For example:
> For length of stay, all the data from different studies were presented 
> in medians and IQR
> For cost, all the data were presented in 'different in cost' and 95% CI
>
> Is there anyway to calculate the pooled effects of the above using Stata?
> If yes, please show me the syntax for such calculations.
> Thank you.
>
> Louisa
>
> *
> *   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/
>   

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