Page 1 of 1

simple regression with no predictors

Posted: Thu Jul 25, 2019 4:43 am
by j0hn
I'm taking the COursera course on logistic regression (https://www.coursera.org/specialization ... lic-health)

One of the first exercises is using this code to create a model with no predictors:

"The “1” is just R’s way of saying that there’s only an intercept term in the model. To get the output, though, you need the “summary” command as well. To do this, you need to make an R object out of the model. I’ve called this object “m”.

glm(dm ~ 1, family=binomial (link=logit))"

Is it possible to do this in jamovi? Looks like something has to be entered as a covariate.

Re: simple regression with no predictors

Posted: Thu Jul 25, 2019 4:48 am
by jonathon
hi,

no sorry, an 'intercept only' model isn't very common in practice. just take a mean, or perform a one-sample t-test.

cheers

jonathon

Re: simple regression with no predictors

Posted: Sun Jul 28, 2019 1:38 am
by j0hn
thanks

Re: simple regression with no predictors

Posted: Fri Sep 20, 2019 12:17 am
by jonathon
i think you can do this in GAMLj though.

cheers