The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.
This makes the comparison of happiness after weighting to be wrong.
The purpose of having the outcome in the target population was to show how adjustment gets us closer there.
This makes the comparison of happiness after weighting to be wrong. The purpose of having the outcome in the target population was to show how adjustment gets us closer there.
This: https://github.com/facebookresearch/balance/blob/main/balance/datasets/__init__.py#L62 Should be made to be like this: https://github.com/facebookresearch/balance/blob/main/balance/datasets/__init__.py#L89
After the change, the seed would change a bit - so tests would need to be fixed.