Consistency without Inference: Instrumental Variables in Practical Application

By Alwyn Young. European Economic Review, 2019

149 citations recorded by the source corpus.

I use Monte Carlo simulations, the jackknife and multiple forms of the bootstrap to study a comprehensive sample of 1309 instrumental variables regressions in 30 papers published in the journals of the American Economic Association. Monte Carlo simulations based upon published regressions show that non-iid error processes in highly leveraged regressions, both prominent features of published work, adversely affect the size and power of IV tests, while increasing the bias and mean squared error of IV relative to OLS. Weak instrument pre-tests based upon F-statistics are found to be largely uninformative of both size and bias. In published papers IV has little power as, despite producing substantively different estimates, it rarely rejects the OLS point estimate or the null that OLS is unbiased, while the statistical significance of excluded instruments is exaggerated. or bias characteristics of regression are by paper leverage (in the on-line appendix) do not find it to be informative in low, medium or high leverage sub-samples. Results for the bias test cannot be meaningfully broken down by leverage group. The 134 regressions for which Stock & Yogo provide bias bounds only cover one high leverage paper and three low leverage papers, and in the latter almost all observations, but for those from one regression, exceed the test bounds.

Subfields: Economics and Econometrics

View Paper: https://www.semanticscholar.org/paper/783ff77c7a5fe961c09c3b7d2a1c9ddc261ec87a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

An Automatic Finite-Sample Robustness Metric: When Can Dropping a Little Data Make a Big Difference? (2020, methodology): “For this reason, a procedure such as IV may be “non-robust” in the sense of having poor coverage in ﬁnite sample (as reported by Young (2019)) and yet be AMIP-robust, or vice versa.”
One Instrument to Rule Them All: The Bias and Coverage of Just-ID IV (2021, background): “4 Young (2022) discusses these problems in an IV context.”
The influence of hidden researcher decisions in applied microeconomics (2020, unknown): “Such metascientific studies in economics sometimes examine published work either through the lens of its unconsidered statistical properties (Ioannidis et al., 2017; Young, 2018).”