hal9001
causalglm
hal9001 | causalglm | |
---|---|---|
1 | 2 | |
48 | 17 | |
- | - | |
5.2 | 0.0 | |
15 days ago | about 2 years ago | |
R | R | |
GNU General Public License v3.0 only | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
hal9001
-
[Q] Should G-methods, IPTW always be used over traditional regression?
Another approach is to make your own SL learner. It turns out to be not as difficult as it may seem to do this. You still pass in the same character string to the SuperLearner functions (e.g. "SL.customlearner") and it will extract the function "SL.customlearner" from your R environment. Here is one example: https://github.com/tlverse/hal9001/blob/devel/R/sl_hal9001.R
causalglm
-
[Q] Sensitivity of (Causal) Inference to Nonlinear Functional Form
Why not both? https://tlverse.org/causalglm/ (Will replace this with a more informative comment when I have free time later today)
-
[Q] Should G-methods, IPTW always be used over traditional regression?
This package: https://github.com/tlverse/causalglm was recently developed to fill the gap between fully black box causal learning methods for heterogeneous treatment effects and fully parametric generalized linear model approaches. It allows for both semiparametric and nonparametric robust causal inference for user defined “working parametric models” for the estimands of interest. It is still black box in that non relevant features of the data distribution are estimated using machine learning but the relevant conditional parameters are modeled fully parametrically (with nonparametric robust inference when misspecified). It is very new so use with caution.
What are some alternatives?
yaglm - A python package for penalized generalized linear models that supports fitting and model selection for structured, adaptive and non-convex penalties.
EconML - ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research project aimed at applying Artificial Intelligence concepts to economic decision making. One of its goals is to build a toolkit that combines state-of-the-art machine learning techniques with econometrics in order to bring automation to complex causal inference problems. To date, the ALICE Python SDK (econml) implements orthogonal machine learning algorithms such as the double machine learning work of Chernozhukov et al. This toolkit is designed to measure the causal effect of some treatment variable(s) t on an outcome variable y, controlling for a set of features x.
tmlenet - Targeted Maximum Likelihood Estimation for Network Data
lmtp - :package: Non-parametric Causal Effects Based on Modified Treatment Policies :crystal_ball:
modeltime - Modeltime unlocks time series forecast models and machine learning in one framework
mlr3learners - Recommended learners for mlr3
drake - An R-focused pipeline toolkit for reproducibility and high-performance computing
modeltime.resample - Resampling Tools for Time Series Forecasting with Modeltime
tweetbotornot2 - 🔍🐦🤖 Detect Twitter Bots!
looper - A resource list for causality in statistics, data science and physics
tmle3mopttx - 🎯 💯 Targeted Learning and Variable Importance for the Causal Effect of an Optimal Individualized Treatment Intervention