A Finite Population Likelihood Ratio Test of the Sharp Null Hypothesis for Compliers

Abstract

In a randomized experiment with noncompliance, scientific interest is often in testing whether the treatment exposure X has an effect on the final outcome Y. We propose a finite-population significance test of the sharp null hypothesis that X has no effect on Y, within the principal stratum of compliers, using a generalized likelihood ratio test. We present a new algorithm that solves the corresponding integer programs.

Cite

Text

Loh and Richardson. "A Finite Population Likelihood Ratio Test of the Sharp Null Hypothesis for Compliers." Conference on Uncertainty in Artificial Intelligence, 2015.

Markdown

[Loh and Richardson. "A Finite Population Likelihood Ratio Test of the Sharp Null Hypothesis for Compliers." Conference on Uncertainty in Artificial Intelligence, 2015.](https://mlanthology.org/uai/2015/loh2015uai-finite/)

BibTeX

@inproceedings{loh2015uai-finite,
  title     = {{A Finite Population Likelihood Ratio Test of the Sharp Null Hypothesis for Compliers}},
  author    = {Loh, Wen Wei and Richardson, Thomas S.},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2015},
  pages     = {523-532},
  url       = {https://mlanthology.org/uai/2015/loh2015uai-finite/}
}