- Rating
- 4(+2)
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3(+2)
Read review
Paper summary
This paper proposes KICS, a test for the conditional exogeneity of a candidate instrumental variable under more flexible structural conditions than previous work and without requiring auxiliary side information. The key idea is that, under conditional exogeneity, reweighting the outcome regression by the squared residual of the candidate IV leaves the regression coefficients unchanged, whereas a violation induces a systematic coefficient discrepancy. Theoretical and empirical results demonstrate that KICS correctly tests conditional exogeneity under specified assumptions, with broader applicability than existing approaches.
Critical strengths
-
Testing IV conditional exogeneity is a long-standing challenge that limits the practical use of IV methods, and the proposed procedure addresses this gap with clear practical value.
-
The core idea, reweighting the outcome regression by the squared residual of the candidate IV leaves coefficients stable under conditional exogeneity but shifts them under a violation, is intuitive and well motivated. While the regression-comparison principle itself builds on KRCD, its IV-specific formulation here is novel.
-
The paper is clearly written and easy to follow.
-
The theoretical analysis is thorough and, under the stated sufficient conditions, correct.
-
The empirical evaluation includes both synthetic and real-data experiments, and the results are convincing.
Critical weaknesses
-
Although adapting the KRCD principle to IV testing is well motivated, the IV setting introduces a subtlety that undermines the direct analogy. Specifically, because the regression input is and is a collider on the path , conditioning on makes and dependent even when the null holds. Thus, in principle, the IV-weighted regression coefficients can differ from the ordinary ones even under conditional exogeneity.
-
The authors avoid this issue by imposing Condition A3 in the appendix, which requires that and do not interact given . This condition is strictly stronger than the null hypothesis itself, is not directly testable since is latent, and appears unlikely to hold in practical IV settings where the collider structure is inherent. In effect, the paper addresses the untestability of conditional exogeneity by assuming another untestable condition.
-
To mitigate this concern, the authors should (i) move Condition A3 to the main text, explain when it is plausible to hold, and discuss whether any diagnostic exists for it; and (ii) add experiments that systematically compare performance when A3 holds versus when it is violated to varying degrees, to clarify the practical robustness of the test.
Questions for authors
Please see Weaknesses.
If the authors can fully address my concern regarding Condition A3, I would consider this a highly interesting and practically valuable work that makes a significant contribution to IV research, and I would be very willing to raise my score.
6 comments
Response to Reviewer 78zy (2/4)
[W2 & W3] Is there an observable diagnostic for A3?
-
Reviewer's concern: A3 involves the unobserved latent confounder , making it difficult to assess directly. The reviewer also asks whether a practical diagnostic is available.
-
Observable diagnostic: To address this concern, we provide an observable conditional-moment representation of A3 and propose a cross-fitting-based diagnostic.
-
Observable conditional moment: Under the outcome model and the noise-orthogonality condition A4,
This equality holds because is fixed given and contributes no conditional covariance, while A4 eliminates the corresponding noise contribution. Thus, the observable outcome can be used to assess the conditional-moment restriction underlying A3.
-
Diagnostic implementation: In practice, cross-fitting can be used to estimate the conditional means of and given . We can then examine whether the conditional expectation of the product of their residuals is close to zero. This allows us to diagnose the moment restriction underlying A3 without directly observing .
-
Diagnostic experiment: We further evaluate this diagnostic using the same collider DGP, fixing and varying to progressively violate A3 while maintaining IV exogeneity. We use cross-fitting to estimate the conditional means and construct a treatment-stratified residual-product diagnostic. With 250 repetitions and , we obtain:
Table 2. Rejection rates of the observable A3 diagnostic.
Diagnostic rejection rate 0.00 0.012 0.20 0.096 0.40 0.392 0.60 0.676 0.80 0.856 1.00 0.948 -
Diagnostic conclusion: The diagnostic exhibits a low rejection rate when A3 holds, while its rejection rate increases substantially as A3 is violated, reaching 0.948 at . These results demonstrate that the observable diagnostic can effectively detect violations of A3.
-
-
Paper Revision. We have revised Appendix D.2 (p. 23, lines 1216–1241; Table 6) to add the observable conditional-moment identity, cross-fitting diagnostic, and numerical evaluation.
Response to Reviewer 78zy (3/4)
[W3] How does KICS behave as A3 is progressively violated?
-
Theoretical insight: Violations of A3 need not induce large coefficient discrepancies. When the weighted Gram matrix is well-conditioned, the population discrepancy is bounded by a constant times , where . Thus, moderate A3 violations can remain within a bounded perturbation regime.
-
Sensitivity experiment: To evaluate the effect of A3 violations on KICS, we use the collider DGP introduced in our [W1 & W2] response.
-
Parameter control: We fix so that the IV remains exogenous and increase to progressively violate A3. A3 holds at ; as increases, treatment depends more strongly on the IV magnitude , inducing conditional dependence between the squared weight and the latent confounder given .
-
Experimental results: Using the same KICS configuration (250 repetitions, linear kernel, , ), we obtain:
Table 3. KICS false-rejection rates under progressive violations of A3.
Detection rate 0.00 0.028 0.10 0.028 0.20 0.024 0.30 0.028 0.40 0.044 0.50 0.052 0.60 0.068 0.70 0.088 0.80 0.112 0.90 0.116 1.00 0.148 -
Experimental conclusion: All IVs remain valid, so the detection rates here measure false rejections. Relative to the nominal significance level , these rates remain within the 95% Monte Carlo fluctuation range through , but exceed it from onward. These results suggest that KICS exhibits some robustness to moderate violations of A3.
-
-
Paper Revision. We have revised Appendix D.3 (p. 24, lines 1242–1271; Table 7) to add the coefficient-discrepancy bound and A3-violation sensitivity experiment.
[W3] Main-text revisions to A3
-
We have moved Condition A3 to the main text and added discussions of its applicability in collider settings, observable diagnostics, the new diagnostic experiment, and the power and A3 sensitivity experiments.
-
Paper Revision. We have revised Section 4.1 (p. 5, lines 260–269; p. 6, lines 282–284) to present and explain the null-side A3 condition in the main text, with supporting details in Appendix A.1.2 (p. 14, lines 726–736) and technical analyses in Appendices D.1–D.3 (pp. 22–24, lines 1177–1271).
Response to Reviewer 78zy (1/4)
We thank the reviewer for the constructive feedback. Our responses are provided below.
Reviewer's concern: The reviewer notes that conditioning on the collider Z→T←UY may induce dependence between Z and UY even under IV exogeneity, potentially causing coefficient discrepancies. Although A3 addresses this issue, the reviewer further questions whether A3 can hold in practical IV settings involving a collider.
Key conclusion: The presence of a collider does not necessarily violate A3.
Theoretical analysis: Collider-induced dependence between Z and UY does not necessarily extend to the squared residual-IV weight RZ2. Specifically, if E[RZ2∣UY,T,X]=E[RZ2∣T,X], then Cov(RZ2,h(UY)∣T,X)=0, so A3 holds even when Z and UY are conditionally dependent.
Construction and validation in a collider setting: To show that A3 can hold despite the collider and to evaluate KICS in this setting, we construct a collider-IV scenario.
Data-generating process (DGP): We construct the IV using a random sign S and a positive random magnitude A. Here S∈{−1,1} is balanced, A is nonconstant, and S,A,U,X are mutually independent, with U∼N(0,1) and X∼N(0,I3). The DGP is
Zγ=SA(1+γU)
T∼Bernoulli(σ(1.4SAκ+U))
Y=0.8T+0.5X1−0.3X2+0.2X3+U+εY.
Theoretical validation: At γ=κ=0, the IV is valid, and both of the following hold:
Collider dependence is present. Because both S and U affect T, conditioning on T induces dependence between Z and U: Cov(Z,U∣T=1)≈−0.163=0.
A3 still holds. Here T depends on the IV sign S, but not its magnitude A. Conditioning on T can therefore associate S with U, but not A2 with U. Since RZ2=A2 and A is independent of (T,X,U), we have Cov(RZ2,U∣T,X)=0. Thus, A3 holds exactly.
This shows that A3 can hold in an IV setting with a collider.
Experimental validation: To further evaluate KICS's detection ability in this setting, we fix κ=0 and increase γ to progressively introduce dependence between the IV and the latent confounder U. Using the same KICS implementation (250 repetitions, linear kernel, P=5, α=0.05), we obtain:
Table 1. KICS detection rates in the collider-IV setting.
Experimental conclusion: In this collider setting, KICS maintains a low false-rejection rate for a valid IV, while its detection rate rises sharply as exogeneity is violated. These results show that KICS can operate effectively in collider settings satisfying A3.
Paper Revision. We have revised Section 4.1 (p. 5, lines 260–269) and added the collider construction and detection experiment in Appendix D.1 (pp. 22–23, lines 1177–1213; Table 5 on p. 23), with the formal A3 statement in Appendix A.1.2 (p. 14, lines 726–736).