-
I'm getting an overparameterized model when I use a constant in OrdinalGEE with independence and naive cov_type.
If I remove the constant, I get identical results to Ordered model with Logit in #70…
-
This would be similar to `integrate_ode` but instead of calling
```
theta
-
just parking a reference:
issue is replicating GLM with GMM, specifically with dispersion modelling, related to Quadratic Estimating Equations.
In Tweedie PR #2872, issue #2858 the question was how …
-
We'll need combined covariance matrix estimates for coefficients fitted with say `lm(y~a.(), ...)` and `lm(y~a.()*sbgrp, ...)`. Or with `lmitt(y~sbgrp1, ...)` and `lmitt(y~sbgrp2,...)`. (For multipl…
-
currently just an idea,
extension to #7793 het models as multilink models
and issue #7639
The multilink/Het models assume that the variance/scale/dispersion depends on exogenous explanatory var…
-
Original question on KPI-ML syntax:
• Formula
Some APM metrics, eg Cost of Unplanned Downtime (CUD), can be calculated with any of several equations, e.g. either as (quantity X estimated average cost…
-
@JohnDenker wrote:
1) In hydrogen, the electrons are marginally relativistic.
2) In lead, the electrons are _more_ relativistic. The gamma-factor
is larger (compared to hydrogen).
3) The book cl…
-
I don't see an open issue for this, and just found a statistics article for it for QIF-GEE
To get started: using principal components
Cho and Qu use principal components on a subset of moment co…
-
I am aware that the default inference implemented is based on Mean squared error (MSE) loss. Is there an implemented example or a way to obtain aleatoric uncertainty instead (either homoscedestic or h…
-
new working assumptions:
"`scale` is an estimated parameter that belongs into the results, and the model is not supposed to keep it as an attribute"
Choice of estimation method for `scale` should be…