Tom Wenseleers

Would it not make sense to clip the returned coefficient estimates within the requested constraints?

For a Firth's penalized multinomial regression there was this now archived R package - but when I tried it was super slow: https://github.com/cran/pmlr and I saw this article: https://www.sciencedirect.com/science/article/pii/S1755534518300836 (I...

Great to hear! I was asking this also in the context of a package I was doing for L0-norm penalized GLMs, ie best subset selection, where I am approximating the...

No worries - it was mainly nonnegativity constraints that I needed - I guess for now I'll just have to clip negative coefficients to zero then...

I was just wondering if there is any update planned to also support observation weights? Is it the case that right now, for family="gaussian", one could pre-multiply X by diag(sqrt(weights))...

Also looking for that! Will support for sparse matrices be added in the future?

Just realise that probably the easiest way to support weights in lm's or nls models would be to multiply both the dependent variable and each of the predictors with the...

Hmm thanks for the bug report. I can confirm that ``` library(Seurat) data("pbmc_small") pl = FeaturePlot(object = pbmc_small, features = 'PC_1') graph2ppt(x=pl, file="./test.pptx", width=7, height=5) ``` also produces the error...

Also just noticed this function https://www.rdocumentation.org/packages/propagate/versions/1.0-5/topics/predictNLS which apparently provides confidence and prediction intervals for nls models using a second order Taylor approximation, https://rmazing.wordpress.com/2013/08/26/predictnls-part-2-taylor-approximation-confidence-intervals-for-nls-models/ https://www.google.be/url?sa=t&rct=j&q=&esrc=s&source=web&cd=9&ved=2ahUKEwjH96uj947aAhUOLFAKHYtVBLUQFjAIegQIABBZ&url=http%3A%2F%2Faustralianantarcticdatacentre.github.io%2FGentleR%2F2014-11-13%2Fnls-vb.docx&usg=AOvVaw2YFbQhRn7O0VRjMsOvBxnO and also supports multiple predictors. Would...

Cool - many thanks for that! If you would be interested in also supporting 2nd order Taylor approximations as opposed to just 1st order for nls models you could always...