Adding a factor to a Bayesian Regression
Hi everyone,
I'm interested in conducting a Bayesian regression analysis. I have various continuous predictors, which I can add as "Covariates". However, I would also like to add Gender, which should be a factor if I'm correct (its a nominal variable). In the regular regression I can do, but not in the Bayesian regression.
Hence, I started programming it in R. However, also here did not succeed to add Gender as a factor haha. I hope someone can help :).
I used the 'bas.lm' function to analyze the posterior probabilities. The Italic items are "covariates"...
BLR <- bas.lm(RT.CIT.effect ~ First.LSRP.score + Second.LSRP.score + BIS.11.score + nogo.errors, data = data, prior = "JZS", modelprior = beta.binomial(1,1), method = "BAS", alpha = 0.125316)
And this is what I wrote to calculate the BF inclusion
pip_vector <- c(0.1729, 0.1547, 0.2247, 0.2250)
prior_odds_inclusion <- 1
prior_odds_exclusion <- 1
bf_inclusion <- pip_vector / (1 - pip_vector) * (prior_odds_inclusion / prior_odds_exclusion)
All help will be greatly appreciated!
Nathalie
Comments
Hi Nathalie,
The issue is that the prior structure on the regression coefficients is of a particular form that assumes the predictors are continuous. Making the methodology work for all kinds of predictors would be very interesting. I would be tempted to pretend that "gender" was a continuous predictor, but that is a hacky solution.
EJ
Thank you EJ!
So, maybe it will be more correct to run a Bayesian ANCOVA?
I can add the continuous variables as covariates, and Gender as a fixed factor (this I can do in JASP). Im just confused with the term "covariate", as in ANCOVA we usually want to control for the Covariate...
Thank you, all help is very much appreciated! :)
Nathalie
Yes, that is correct
EJ