Hello Victor,

This one is new to me as well, but what it sounds like is that author/s have ranked IVs relative to one another (see link below for an example of this type of thinking). Whether that makes sense for "multivariate [sic; more likely multivariable] adjusted risk estimates" when such estimates are highly dependent on the specific sift of variables included is debatable.

In any event, it would be fair game to ask author/s to offer some justification for opting for this step.

Good luck with your work.

Article An Extended TODIM Method with Unknown Weight Information Und...

Thanks a lot David!

I believe this is a confusion likely influenced by the terminology used in inheritance analyses. I'll comment on this to the authors. There is a common misuse of the terms "multivariate" and "multivariable" in the literature. Thanks for pointing this as well.

V.

It seems like you are editing a meta-analysis that reports the use of dominance ratio (OR) as a general measure of association in the collection of multivariate-adjusted risk estimates (OR or HR values) from individual studies. The use of the dominance ratio as a measure of association is not very common in the meta-analysis, but it can be useful when the data do not meet the assumptions of traditional measures of association, such as odds ratios or hazard ratios.

The dominance ratio is a non-parametric measure of association that is based on the comparison of two groups or categories. It is calculated by dividing the proportion of cases in which the exposure is dominant (i.e., more prevalent) in the group with the outcome by the proportion of cases in which the exposure is dominant in the group without the outcome. The dominance ratio can range from 0 to infinity, with values greater than 1 indicating a positive association between the exposure and the outcome.

When reporting the results of a meta-analysis that uses the dominance ratio as a measure of association, it is important to provide a clear explanation of how the measure was calculated and how it was used to collect the risk estimates from individual studies. You should also report the 95% confidence interval (CI) for the dominance ratio, which can be calculated using a standard formula or by using a bootstrapping procedure.

In summary, the dominance ratio can be a useful measure of association in a meta-analysis when traditional measures of association cannot be used, but it is important to provide a clear explanation of its use and interpretation in the reporting of results.

Thank you so much Ma'Mon for claryfing this concept.

It is still confusing that they use OR to abbreviate dominance ratio...

Kind Regards,

Victor