Keita Sunada, Yukitoshi Matsushita, Taisuke Otsu
arXiv 5 Oct 2026 · Econometrics
arXiv:2610.06119 · PDF · Extracted main text
Quadratic-form test statistics are widely used in econometrics, and their performance depends on accurate variance estimation. Conventional plug-in estimators are consistent under the null hypothesis, but under alternatives the drift in the residuals inflates them and the test loses power. We develop a general framework for variance estimation in such statistics, replacing one of the two squared-residual factors by an auxiliary linear combination of the residuals (“cross-fitting”) chosen to annihilate the drift. We characterize the conditional bias of each estimator exactly. The drift enters the plug-in estimator squared, multiplied by quantities bounded away from zero, so its bias is positive whenever the drift is non-degenerate. It reaches the cross-fit estimator only through the part that survives the cross-fitting, and then only through off-diagonal entries of a residual-maker matrix. From this calculation we obtain conditions under which the cross-fit estimator remains consistent under alternatives while the plug-in estimator does not. At a common critical value the cross-fit test therefore rejects whenever the plug-in test does, and against distant alternatives the plug-in statistic converges to a finite limit, small when few observations carry the departure: its power can tend to zero where the cross-fit test's tends to one. We verify the conditions under primitive assumptions in nonparametric specification testing, overidentification testing, and testing many linear restrictions, and illustrate the procedure on the Oregon Health Insurance Experiment.
appendix boundary found by appendix_command · 47% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Chao, John C., Hausman, Jerry A., Newey, Whitney K., Swanson, Norman… (2014) Testing overidentifying restrictions with many instruments and heteroskedasticity | 1.000 | 9 | 3 | 100% |
| 2 | Anatolyev, Stanislav (2023) Testing many restrictions under heteroskedasticity | 0.946 | 13 | 5 | 85% |
| 3 | Sun, Yiguo, Li, Qi (2006) An alternative series based consistent model specification test | 0.928 | 4 | 3 | 100% |
| 4 | Mikusheva, Anna, Sun, Liyang (2022) Inference with many weak instruments | 0.714 | 11 | 5 | 36% |
| 5 | Hausman, Jerry A., Newey, Whitney K., Woutersen, Tiemen, Chao, John… (2012) Instrumental variable estimation with heteroskedasticity and many instruments | 0.644 | 2 | 2 | 100% |
| 6 | Hong, Yongmiao, White, Halbert (1995) Consistent specification testing via nonparametric series regression | 0.644 | 2 | 2 | 100% |
| 7 | Jochmans, Koen (2022) Heteroscedasticity-robust inference in linear regression models with many covariates | 0.511 | 2 | 1 | 100% |
| 8 | Anatolyev, Stanislav, Gospodinov, Nikolay (2011) Specification testing in models with many instruments | 0.405 | 1 | 1 | 100% |
| 9 | Anatolyev, Stanislav, Korobka, Aleksandr (2026) Parameter-invariant unbiased estimation of individual variances and their pairwise products | 0.405 | 1 | 1 | 100% |
| 10 | Boot, Tom (2023) Joint inference based on Stein-type averaging estimators in the linear regression model | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 21 scored citations.