[R-meta] Inquiry on metafor trimfill
Ruecker @ending from imbi@uni-freiburg@de
Sat Sep 22 16:11:57 CEST 2018
You may be interested in having a look at a more recent article:
Veroniki AA, Jackson D, Viechtbauer W, Bender R, Bowden J, Knapp G, et al. Methods to estimate the between-study variance and its uncertainty in meta-analysis. Res Syn Meth 2016; 7(1): 55-79.
Von: Michael Dewey [lists using dewey.myzen.co.uk ]
An: Chishio Furukawa [chishio.furukawa using gmail.com ], R meta [r-sig-meta-analysis using r-project.org ]
Datum: Sat, 22 Sep 2018 13:43:22 +0100
> Dear Chisio
> I think the answer to your question is probably "No". Although it is 13
> years old I think Wolfgang's article cited in the help page of rma.uni
> as Viechtbauer (2005) gives that advice. Worth reading (or re-reading)
> On 22/09/2018 01:12, Chishio Furukawa wrote:
>> Dear all,
>> I used the "trifill" command in the metafor package, which provided various
>> options for estimating the heterogeneity across studies. My objective was
>> to estimate the coverage probabilities of the trim-and-fill method (Duval
>> and Tweedie 2000) for comparison with other methods.
>> Given the original article in 2000, I think it is adequate to use "DL"
>> command (standing for formula in DerSimonian and Laird 1996), but I was not
>> confident what methodology is most commonly used. Could I ask if there are
>> recommendations on which formula to use among HS, HE, SJ, ML, REML, and EB?
>> It appears that the estimation result of coverage probability can change
>> importantly depending on which method to use.
>> Thank you!
>> Best regards,
Institute of Medical Biometry and Statistics,
Faculty of Medicine and Medical Center - University of Freiburg
Postal Address: Stefan-Meier-Str. 26, 79104 Freiburg
Phone: +49/761/ 203-6673
Mail: Ruecker using imbi.uni-freiburg.de Homepage: http://www.imbi.uni-freiburg.de
More information about the R-sig-meta-analysis