Comments (5)
As a further note to self, this paper also describes a different approach to estimating the g-formula. It might be an easier approach to code and involves less model specification for users
Essentially, you go back through time fitting an outcome model at the last time point, generate your predictions then keep working backwards. This approach relies on a clever covariate to become doubly-robust and semi-parametric. https://www.jstor.org/stable/27645860?seq=1#metadata_info_tab_contents
This is useful background to consider for the LTMLE as well, since it uses a similar estimation process
from zepid.
Adapt code from g-formula sequential regression estimator part of #30 and #32
from zepid.
Bumping the LTMLE implementation timeline back. Will be added after 0.4.0 since it will take me some additional time to implement (and I would like to release 0.4.0 soon)
from zepid.
Estimation of g_t is IPTW for follow-up (cumulative product). Need to estimate the IPTW for each time point. Likely best if I fit a model to each time point for this estimation. This will make no parametric assumptions regarding time (however some models might not fit).
Maybe later create a work around that allows for parametric time?...
from zepid.
https://arxiv.org/abs/1802.05005
from zepid.
Related Issues (20)
- IPTW handle PerfectSeparationErrors in the marginal structural model better
- AIPW for survival analysis ? HOT 1
- Dual treatments
- ValueError better pytest strategy
- Package compatibility? HOT 2
- Update documentation (and possibly re-organize) HOT 2
- MonteCarloGFormula
- Add Odds Ratio and other estimands for AIPTW and TMLE
- Addition of meta-analysis tools
- add p-value column in a forrest plot/ effectmeasureplot HOT 2
- Enhancement in graphics.py to change odds text size HOT 1
- Saving DAGs programatically HOT 11
- sklearn dependancy in setup.py should be scikit-learn HOT 1
- AIPW formula equivalent to what's in the literature? HOT 2
- Perfect separation error for using `SingleCrossfitTMLE` HOT 2
- Superlearn check weights HOT 2
- SingleCrossFit `invalid value encountered in log` HOT 8
- Unable to install latest 0.9.0 version through pip HOT 7
- Risk Ratio Summary HOT 1
- The default regression argument of zepid.base.interaction_contrast_ratio differs from the description in the documentation. HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from zepid.