Rethinking Nonlinear Instrumental Variables

dc.contributor.advisor

Rudin, Cynthia

dc.contributor.advisor

Dunson, David

dc.contributor.author

Li, Chunxiao

dc.date.accessioned

2019-06-07T19:51:18Z

dc.date.available

2019-06-07T19:51:18Z

dc.date.issued

2019

dc.department

Statistical Science

dc.description.abstract

Instrumental variable (IV) models are widely used in the social and health sciences in situations where a researcher would like to measure a causal eect but cannot perform an experiment. Formally checking the assumptions of an IV model with a given dataset is impossible, leading many researchers to take as given a linear functional form and two-stage least squares tting procedure. In this paper, we propose a method for evaluating the validity of IV models using observed data and show that, in some cases, a more flexible nonlinear model can address violations of the IV conditions. We also develop a test that detects violations in the instrument that are present in the observed data. We introduce a new version of the validity check that is suitable for machine learning and provides optimization-based techniques to answer these questions. We demonstrate the method using both the simulated data and a real-world dataset.

dc.identifier.uri

https://hdl.handle.net/10161/18898

dc.subject

Statistics

dc.subject

Causal Inference

dc.subject

Instrumental Variable

dc.subject

Machine Learning

dc.title

Rethinking Nonlinear Instrumental Variables

dc.type

Master's thesis

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Li_duke_0066N_15146.pdf
Size:
1.24 MB
Format:
Adobe Portable Document Format

Collections