Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

require dependent variable to be passed to the model to avoid specifying it in the formula #79

Closed
GidonFrischkorn opened this issue Feb 9, 2024 · 6 comments · Fixed by #92
Assignees
Labels
PR - minor Pull-request should update minor version
Milestone

Comments

@GidonFrischkorn
Copy link
Collaborator

  • dv as required argument
  • add option to predict the location of the target distribution in the mixture models
@GidonFrischkorn GidonFrischkorn added the PR - minor Pull-request should update minor version label Feb 9, 2024
@GidonFrischkorn GidonFrischkorn added this to the 1.0.0 milestone Feb 9, 2024
@GidonFrischkorn GidonFrischkorn self-assigned this Feb 9, 2024
@venpopov
Copy link
Owner

venpopov commented Feb 9, 2024

one solution to the problem you told me at lunch would be write a bmm formula function similar to brms::bf, in which we have more flexibility, though I suspect this might be a lot of work and not sure if it's worth it. Just an idea

@venpopov
Copy link
Owner

venpopov commented Feb 9, 2024

although maybe we should stick with the current syntax to be consistent with brms

@GidonFrischkorn
Copy link
Collaborator Author

Yes, I thought a bit about possible solutions as well, but did not come up with one yet. I will have to look into this in more detail for the ezDM implementations anyway. But for now, I would keep the formula syntax the way it is.

@GidonFrischkorn
Copy link
Collaborator Author

GidonFrischkorn commented Feb 9, 2024

I have looked a bit into the object created by the brmsformula function. And think there might be an easier solution than initially thought to this problem. I will explore it a little, but in short: The bf function separates the first formula as the "main" formula and stores the rest of the formulas in an additional list labeled pforms. I assume this is an abbrehviation for parameter formulas.

I think it should be possible to write a simple bmm_formula function that creates this list taking in the same type of formulas that the brmsformula function takes in. And then we can actually just add the correctly formatted list into the formula$pforms list.

I will check this out at the beginning of next week and keep you updated.

@venpopov
Copy link
Owner

venpopov commented Feb 9, 2024

that's along the lines of what I was thinking above. Glad to hear it is simpler than expected!

@GidonFrischkorn
Copy link
Collaborator Author

I had a bit of time to look into this and thing I should be able to provide a solution. This also entails checking if formulas for all model parameters were specified and throwing a warning if this is not the case while only estimating a fixed intercept for them.

I will keep you posted on the progress and then we can see, if the solution seems feasible for all models and also in the long run.

But for some models, such as The ezDM, I will certainly use this functionality. So, I will keep exploring this anyway.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
PR - minor Pull-request should update minor version
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants