Skip to content

[R-meta] Network Meta Analysis with multiple Time points

5 messages · Wolfgang Viechtbauer, t@s@ueressig m@iii@g oii gmx@de, Nicky Welton

Wolfgang Viechtbauer
# 
Dear Tobis,

Please register to post to the mailing list.

As for your question: Yes, metafor can in principle do this. You would have to combine methods from these examples:

https://wviechtb.github.io/metafor/reference/dat.fine1993.html
https://wviechtb.github.io/metafor/reference/dat.ishak2007.html

(which deal with multiple estimates from the same study/group over time) with methods from these examples:

https://wviechtb.github.io/metafor/reference/dat.hasselblad1998.html
https://wviechtb.github.io/metafor/reference/dat.senn2013.html

(which are examples of network MAs).

I do not have any concrete examples to illustrate this though.

You could also look into these articles:

Dakin, H. A., Welton, N. J., Ades, A. E., Collins, S., Orme, M., & Kelly, S. (2011). Mixed treatment comparison of repeated measurements of a continuous endpoint: An example using topical treatments for primary open-angle glaucoma and ocular hypertension. Statistics in Medicine, 30(20), 2511-2535.

Ding, Y., & Fu, H. (2013). Bayesian indirect and mixed treatment comparisons across longitudinal time points. Statistics in Medicine, 32(15), 2613-2628.

Jansen, J. P., Vieira, M. C., & Cope, S. (2015). Network meta-analysis of longitudinal data using fractional polynomials. Statistics in Medicine, 34(15), 2294-2311.

They might provide code/examples. I think all of them use a Bayesian framework for model fitting.

Best,
Wolfgang
Nicky Welton
# 
Dear Tobias,

If you want to fit a functional relationship between the relative effects and time, there is an R package for modelling time-course in Network Meta-Analysis (time MBNMA):

https://CRAN.R-project.org/package=MBNMAtime<https://cran.r-project.org/package=MBNMAtime>

The methods are described here:

https://onlinelibrary.wiley.com/doi/abs/10.1002/jrsm.1351

Best wishes,

Nicky



From: R-sig-meta-analysis <r-sig-meta-analysis-bounces at r-project.org> On Behalf Of t.saueressig at gmx.de
Sent: 07 October 2020 15:33
To: r-sig-meta-analysis at r-project.org
Subject: [R-meta] Network Meta Analysis with multiple Time points

Hello All,

I have question concerning a network Meta analysis that contains studies which measure their results at multiple time points. Which package can deal with this sort of Data? I know metafor can handle multiple time points in pairwise MA via multivariate methods. So it is probably possible to do that too? Are there any examples how to do that?


Regards

Tobias