-
[GMV.pdf](https://github.com/satrapade/pairs/files/2155920/GMV.pdf)
-
Kyle found that relaxed lasso worked better than regular lasso in some situations. This should be evaluated more carefully. If the relaxed lasso generally outperforms the regular lasso, then it should…
-
**Is your feature request related to a problem? Please describe.**
The current LASSO technically is invalid with the sandwich. That is because the score is not differentiable at zero. There are alt…
-
One topic that isn't touched upon is confounding variables. I've use models selection on them in the past, because I don't really care about them, but some might be important and dropping minor confou…
-
`B_full = M * B_reduced`
example: MNLogit reduced to stereotype Logit, `slogit` in Stata
but this also has the same structure as cointegrating regression (VAR).
see slogit references, and similar m…
-
More and more I find myself using a bizarre mixture of `lm`, `glm`, `glmnet`, `sandwich` (HC1 standard errors), and `lme4/rstanarm` (mixed models) when working with a set of models that are only sligh…
-
Consider that we are only interested in a few parameters in a (linear or non-gaussian) regression model, but have a large number of possible extra explanatory variables (confounders/controls).
What…
-
Hi @privefl , @tshmak
I am benchmarking PRS/PGS methods practiced in the [PRS tutorial](https://choishingwan.github.io/PRS-Tutorial/). Regard to Lassosum, I got some confusions. I'd appreciate if…
-
Is regularization possible in competing risk frailty models? The documentation mentions the LASSO in the `ahaz` package, but as far as I can tell, `ahaz` can't handle that sort of model?
Thanks!
-
Suppose we only have "wrong" models, what's the "best" model and our "best" estimates?
And, how do you define "best"?
Motivation:
Gamma regression: Greene compares MLE versus GMM, where GMM uses ove…