Dear Aethele,

I think the following links will help you

https://www.google.com.tr/amp/s/www.researchgate.net/post/When_should_we_use_a_risk_ratio_odds_ratio_and_relative_ratio_in_the_meta-analysis_to_compare_between_2_predictors_variables/amp

https://www.google.com.tr/amp/s/www.researchgate.net/post/When_to_use_the_odds_ratio_or_the_relative_risk/amp

Thank you Taha Eser, but my main question was about Risk difference, when is it appropriate to use it rather than RR? can you advice?

Taha Eser

Please check these papers. I hope they work:

https://www.theanalysisfactor.com/the-difference-between-relative-risk-and-odds-ratios/

https://academic.oup.com/ndt/article/32/suppl_2/ii13/3056571

Taha Eser thank you

but my question is how to interpret results from the same review in which the results have a RR that is not significant (CI includes 1), but a Risk difference that is significant (CI excludes 0).

You only have to be sure that you interpret either one correctly. This is the advice given by Schmidt & Kohlmann (See below). Given that the relative risk is more intuitive, then it may be more advisable to use it. At least, this is the advice given by Deeks (See below)

Schmidt, C. O., & Kohlmann, T. (2008). When to use the odds ratio or the relative risk? International Journal of Public Health, 53(3), 165–167. https://doi.org/10.1007/s00038-008-7068-3

Deeks, J. (1998). When can odds ratios mislead? Odds ratios should be used only in case-control studies and logistic regression analyses. BMJ (Clinical Research Ed.), 317(7166), 1155-6-7. Retrieved from http://www.ncbi.nlm.nih.gov/pubmed/9784470

I haven't looked at the advice given by Schmidt&al. and by Deeks: probably useful texts for making sure that you interpret either measure correctly, as stressed by Taha E.

However, as regards practical statistical inference, your problem falls under the heading: What to do if one has made two statistical tests of essentially the same hypothesis and obtained (quasi-)conflicting answers? Here theory cannot help you, only subject-matter insight. And one thing more: remember that a statistical test is a STATISTICAL test, not a sharp knife but one as dull as random error (the CI width!) suggests.

Jørgen Hilden , thank you so much . I have reached a similar conclusion. I will use both and discuss the uncertainty .