[R-meta] Changing the reference group within a study

[Viechtbauer, Wolfgang (SP)]

Dear Steven,

1. is p1 / p4
2. is p2 / p4
3. is p3 / p4

So, p4 / p1 is just the reciprocal of 1. (i.e. 1/.81).

The rest is just some simple algebra:

(p2/p4) / (p1/p4) = p2 / p1
(p3/p4) / (p1/p4) = p3 / p1

Best,
Wolfgang

-----Original Message-----
From: R-sig-meta-analysis [mailto:r-sig-meta-analysis-bounces using r-project.org] On Behalf Of Steven Bradburn
Sent: Wednesday, 25 July, 2018 16:24
To: r-sig-meta-analysis using r-project.org
Subject: [R-meta] Changing the reference group within a study

Dear All,

Basically, I was wondering how to change the effect size of an adjusted model from a study to reflect a different reference group within that study. For example, the study has 4 groups with the following relative risks and 95% CIs :

1. RR 0.81 (0.69 - 0.96)

2. RR 0.88 (0.76 - 1.03)

3. RR 0.80 (0.80 - 1.08)

4. Reference

The other studies included within my meta-analysis have defined group 1 as the reference, instead of group 4 used here. How can I go about changing the RRs so that group 1 is the reference group within this study? Or is that not even possible?

Any help on this issue will be greatly appreciated.

Kind regards,

Steven