Stack Exchange network consists of 183 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.
Or could I just show the pattern of Rho results without any tests and explain that Rho = .90 (e.g.) suggests a stronger estimated random effects correlation between the two variables than Rho = .70 (e.g.). We are interested in which variables selected for sensitivity analyses improve the correlations from the overall model.
Oh boy, I've been interpreting this wrong then, but thanks for the helpful explanation. What if I don't necessarily want to test the correlations, but want to compare their magnitude across models. . e.g. I ran an overall multivariate meta-analysis model which is actually the output above (just the correlation part). Now say I've run sensitivity analyses for the meta-analysis - all of models produce different Rho values as per the criteria I've selected for sensitivity. . Can I compare the correlations produced by the overall model with correlations in the sensitivity models some how?
Thanks, that is a helpful reframe of what is happening, I had trouble interpreting that part of the document. And I've updated my model to include the random effects as well. So, if the zero-inflation is predicting likelihood of 0 vs. not-zero, is the conditional model just predicting 0 vs. 1 like a true logistic regression?
Okay so I made some progress on understanding the model. You need both the conditional and zero-inflated outputs because... - the conditional output represents the zero portion (or a logistic regression) - the zero inflated output represents a "mixture" model of the two distributions - one for the subgroup who reports zero or close to zero and one for the subgroup who doesn't report zero. However, my collaborator was wondering whether the zero-inflated portion of the model predicts likelihood of a zero value or likelihood of a 1 value? Or is it truly in between 0 to 1.
