search

rs-station / careless

Merge X-ray diffraction data with Wilson's priors, variational inference, and metadata
MIT License
16 stars 6 forks source link

warning about r>1 or r<0? #147

Closed DHekstra closed 3 days ago

DHekstra commented 9 months ago

motivated by some intrepid users: double-wilson parameters < 0 or >1 are not intended use cases and may lead to unexpected behavior. Perhaps the default should be to resort to univariate priors for negative r and throw an error for r>1?

kmdalton commented 9 months ago

Without thinking too hard, I feel negative values should be a warning. I can't say for sure there is no legitimate use case for negative correlation coefficients. Greater than one being an error makes sense to me.

kmdalton commented 3 days ago

resolved by #170