Please give me some advice.

I am using brms package and mgcv package for two regression models:

  • bernoulli
  • lognormal

The problem is that both of these models outputs are in lognormal scale. As much as I understand, these plots shows a relationship between the predictor b-coefficient (x-axis) on the outcome variable (y-axis). Intercept is not included in this plot.

enter image description here

The problem is that readers won't understand much if the y-axis is on log-scale. What tricks and techniques or bypasses can be used to turn it into an understandable scale (e.g. original scale, OR, probability etc)?

  • $\begingroup$ You need to tell us some context, like the model you have actually estimated? Please edit your post, not only give new info as a comment! $\endgroup$ – kjetil b halvorsen Oct 27 at 12:31

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.