-
Hello.
I am running the example here: https://github.com/microsoft/EconML/blob/master/notebooks/CustomerScenarios/Case%20Study%20-%20Customer%20Segmentation%20at%20An%20Online%20Media%20Company.ipy…
-
I'm using ggpredict() to estimate the response from the glm() but the output from ggpredict reports the se for the prediction on the logit scale and not the [0.1] scale. A MWE is attached.
[ggeffe…
-
Thanks for your work on the margins package.
We would like to estimate average treatment effects on a different population than our survey population. One technique to do this is poststratification…
-
(mainly parking idea and references and links)
Stata has suest command to provide inference for combining tw or more models
Wooldridge mentioned in a tweet that suest cannot be used for post-estim…
-
https://github.com/jeremysze/LPIS/blob/d91897f809ccf55b52f6a089c639c79bf316abcd/analysis_qt_panel_3b.ipynb
Under Time Trends, I ran the interaction of flag_school (intersections within 200ft of sch…
-
I have a dataset of about 400 thousand observations. It is not too large, at around 100 MB of space. Version is 0.8.0. Unfortunately, as data is confidential, I cannot include it, but I include the co…
-
similar to #8765 but when "treatment" and outcome are binary.
recursive, triangular
y1 = 1(α y2 + x1 β + ε1 ≥ 0)
y2 = 1(x2 β2 + ε2 ≥ 0)
ε1, ε2 are correlated
full, parametric MLE but with cop…
-
Hi @kaneplusplus ,
I use `library(bigmemory)` in my package [bigKRLS](https://github.com/rdrr1990/bigKRLS) (with @rbshaffer) (and it's been highly effective, increasing what a typical laptop can do…
-
When I add priors to glmmTMB, I sometimes can unexpected logLik outputs, especially when the model has many parameters. An inspection of `logLik.glmmTMB` seems to indicate that it uses the `fit$object…
-
Hi @strengejacke
There are a few problems with ggeffects() of a lme() model
1. Given the latest {insight}, ggeffects sometimes produce errors with lme() if its weights = varFunc() is specified.…