Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Supported by

Bayesian logistic regression

Hi,

I was wondering if anyone had any experience of conducting Bayesian Logistic regressions, in JASP or R. In JASP there's no obvious way to do it (although you could do a bayesian linear regression and set the categorical variable to scale. In R there's no widely used/accessible package that I can see either. Does anyone have any advice on how to conduct Bayesian logistic regressions?

Thank you

Comments

  • You can take a look at the R package brms. They have very similar syntax to lmer in terms of writing model formula. Here is a short tutorial of how to fit non-linear models I found online https://cran.r-project.org/web/packages/brms/vignettes/brms_nonlinear.html

  • Yes, brms is the ticket. However, the package places less emphasis on testing, and setting the default priors well (for testing) can take some tinkering. It is in the works for JASP, but not in there yet.

    Cheers,
    E.J.

  • Are there any updates on Bayesian logistic regression in JASP? I would be keen on it as well.

  • Soon...(this year for sure)

  • That's exciting! :-)

  • Hi E.J.,

    Is there any update on Bayesian logistic regression in JASP? Do you know when this will be made available? Alternatively, is there an R method you can recommend for doing Bayesian logistic regression?

    Many thanks.

    Regards,

    Tom

  • Hi Tom,

    Yes, we hope to add this functionality soon. The implementation will be along the same lines as linear regression, so we will also be using Merlise Clyde's BAS package from R. Highly recommended.

    Cheers,

    E.J.

  • Hi EJ,

    Many thanks for your response on this. Hopefully, this will not take long before it is added to JASP.

    Best wishes,

    Tom

Sign In or Register to comment.