-
The variance-covariance estimates (and the standard errors derived from their diagonal) can differ by quite some margin (10-20%) from those of statsmodels, see the example below. Is this as expec…
-
Although it is true that Rust does not support structural subtyping nor record subtyping, it does support nominal subtyping with regard to the relationship between structs (or traits) and the trait th…
-
The suggested way to calculate the 2-way ANOVA with your software is to first fit the linear model via `ols('rez ~ C(A) + C(B) + C(C)', data).fit()`. In my case of 3D fit with dimensions (400, 200, 48…
-
Hello,
I started looking at your code and doc. I have seen the impressive amount of work done on improving the robustness and the speed of the code.
I couldn't find much information about the po…
gh4ag updated
3 years ago
-
I need to perform a Poisson regression on data with around 80,000 dummy variables used to capture two different fixed effects parameters in the model, but get a memory error when trying to do so.
T…
-
I am computing two random matrices that are different and totally random. Their CCA shouldn't be high since they are different and random. Google's svcca library gives me much lower CCA values but ana…
-
The issue is best explained with code, here is a minimal reproduction of the issue.
What is the the output of the following code?
```dart
abstract class Stated {
const Stated._();
fact…
-
HI! Loving this. Trying to put together something for a manuscript that shows the cover of different species based on models, but, I notice `predict.gllvm()` doesn't have an option to get fit error on…
-
Thanks for your effort.
However, when I run the package I face the following Error:
```
[ WARN] [1533199508.052997875, 963.860000000]: Timed out waiting for transform from base_footprint to map…
-
## Proposal
Typically, interrupted time series (ITS) designs are univariate in that there is a single outcome variable. An existing example in the docs examines the causal impact of the onset of covi…