itsdfish / SequentialSamplingModels.jl

A unified interface for simulating and evaluating sequential sampling models in Julia.
https://itsdfish.github.io/SequentialSamplingModels.jl/dev/
MIT License
27 stars 4 forks source link

Docs improvement: write the domain of parameters #97

Closed DominiqueMakowski closed 2 months ago

DominiqueMakowski commented 2 months ago

Something that would be useful to add in the documentation as well as the docstrings, on top of "typical range" as we discussed previously, would be the domain. Which parameters are defined [-Inf, Inf], which must be > 0, etc. This would be helpful for parametrization and would save some thinking and testing (especially when doing specifying lots of different types of models).

kiante-fernandez commented 2 months ago

Putting citations for studies looking at priors in the thread. Would the idea be to have a section in each model that gives those ranges/domains or just add to the explanation of each parameter?

Matzke, D., & Wagenmakers, E. J. (2009). Psychological interpretation of the ex-Gaussian and shifted Wald parameters: A diffusion model analysis. Psychonomic Bulletin & Review, 16, 798-817.

Tran, N. H., Van Maanen, L., Heathcote, A., & Matzke, D. (2021). Systematic parameter reviews in cognitive modeling: Towards a robust and cumulative characterization of psychological processes in the diffusion decision model. Frontiers in Psychology, 11, 608287.

DominiqueMakowski commented 2 months ago

Would the idea be to have a section in each model that gives those ranges/domains or just add to the explanation of each parameter?

🤷 I think adding the info under each parameter section is fine (https://itsdfish.github.io/SequentialSamplingModels.jl/dev/wald/#Non-Decision-Time)

itsdfish commented 2 months ago

It might be useful to list the domain in the doc strings as a convienent reference, and inlclude details about priors in the online documentation.

itsdfish commented 2 months ago

I added parameter bounds to the doc strings. Providing guidance on typical ranges and/or priors to the online documentation would be a lot of work. I'll let someone reopen this issue if they want to submit a PR.