Critical Finance Review > Vol 14 > Issue 1

A Powerful Test Needs to Be Size-Correct: Response to “Robust Inference for Consumption-Based Asset Pricing with Power”

Frank Kleibergen, University of Amsterdam, The Netherlands, f.r.kleibergen@uva.nl , Zhaoguo Zhan, Kennesaw State University, USA, zzhan@kennesaw.edu
 
Suggested Citation
Frank Kleibergen and Zhaoguo Zhan (2025), "A Powerful Test Needs to Be Size-Correct: Response to “Robust Inference for Consumption-Based Asset Pricing with Power”", Critical Finance Review: Vol. 14: No. 1, pp 179-185. http://dx.doi.org/10.1561/104.00000155

Publication Date: 19 Mar 2025
© 2025 Frank Kleibergen and Zhaoguo Zhan
 
Subjects
 
Keywords
C12G12
Identification robust inferenceSize-correctRisk premia
 

Share

Download article
In this article:
1. Size vs. Power 
2. Rank of the Beta Matrix vs. Univariate Beta 
3. Misspecification 
4. Validity of the Bootstrap 
5. Nonlinear GMM-AR and Rank Tests 
6. Conclusions 
References 

Abstract

Statistical tests need to be size-correct, i.e., their rejection frequencies under the null hypothesis should not exceed the nominal significance level, before we can talk about their power. It is well established in the weak identification literature that commonly used t-tests (such as the Fama–MacBeth/Shanken and generalized method of moments (GMM) t-tests) exhibit size distortion when identification conditions are at risk, while identification-robust tests remain size-correct. Furthermore, this literature has also produced tests that are both size-correct and optimal in terms of power. Therefore, these robust tests should be recommended over t-tests, and not vice versa.

DOI:10.1561/104.00000155