A new measure of partial conditional mean independence in Hilbert spaces

i

This article has been updated. A Correction to this article was published on .

i

The Original Article was published on

i

The Original Article was published on

i

This article has been updated

i

This article was retracted on

i

This article has been updated

Abstract

A novel metric, called partial martingale difference-angle divergence, is proposed to test and measure partial conditional mean (in)dependence for Hilbert elements. The partial martingale difference-angle divergence has some appealing properties. It is nonnegative and equals zero if and only if the partial conditional mean independence holds; it has a simple expectation form; it does not require the moment condition for the predictor variable. We construct an estimator for partial martingale difference-angle divergence and derive its asymptotic properties. Finite sample simulations show that the proposed test performs well and has strong testing power for nonlinear relationships. Two real data examples are introduced to illustrate the application of the proposed test.

Keywords

partial conditional mean independence / functional data / V-statistic / nonlinear relationship / permutation test

CHANGE HISTORY

A Correction to this paper has been published:
https://doi.org

The Retraction Note was updated to reflect reception of statements of disagreement from all authors.

This article has been retracted.Please see the Retraction Notice for more detail:
https://doi.org

References

[1] M. A. Delgado, W. G. Manteiga, Significance testing in nonparametric regression based on the bootstrap, Ann. Stat., 29 (2001), 1469-1507. https://doi.org/10.1214/aos/1013203462

[2] Y. Fan, Q. Li, Consistent model specification tests: omitted variables and semiparametric functional forms, Econometrica, 64 (1996), 865-890. https://doi.org/10.2307/2171848

[3] X. Shao, J. Zhang, Martingale difference correlation and its use in high-dimensional variable screening, J. Am. Stat. Assoc., 109 (2014), 1302-1318. https://doi.org/10.1080/01621459.2014.887012

[4] C. E. Lee, X. Zhang, X. Shao, Testing conditional mean independence for functional data, Biometrika, 107 (2020), 331-346. https://doi.org/10.1093/biomet/asz070

[5] T. Lai, Z. Zhang, Y. Wang, A kernel-based measure for conditional mean dependence, Comput. Stat. Data Anal., 160 (2021), 107246. https://doi.org/10.1016/j.csda.2021.107246

[6] T. Lai, Z. Zhang, Local influence detection of conditional mean dependence, Commun. Math. Stat., 11 (2023), 1-27. https://doi.org/10.1007/s40304-023-00365-3

[7] T. Zhou, L. Zhu, C. Xu, R. Li, Model-free forward screening via cumulative divergence, J. Am. Stat. Assoc., 115 (2020), 1393-1405. https://doi.org/10.1080/01621459.2019.1632078

[8] L. Su, X. Zheng, A martingale-difference-divergence-based test for specification, Econ. Lett., 156 (2017), 162-167. https://doi.org/10.1016/j.econlet.2017.05.002

[9] Z. Tian, T. Lai, Z. Zhang, Variation of conditional mean and its application in ultra-high dimensional feature screening, Commun. Stat. Theory Methods, 54 (2024), 352-382. https://doi.org/10.1080/03610926.2024.2310690

[10] T. Park, X. Shao, S. Yao, Partial martingale difference correlation, Electron. J. Stat., 9 (2015), 1492-1517. https://doi.org/10.1214/15-EJS1047

[11] G. J. Székely, M. L. Rizzo, Partial distance correlation with methods for dissimilarities, Ann. Stat., 42 (2014), 2382-2412. https://doi.org/10.1214/14-AOS1255

[12] L. Cai, X. Guo, W. Zhong, Test and measure for partial mean dependence based on machine learning methods, J. Am. Stat. Assoc., 120 (2025), 833-845. https://doi.org/10.1080/01621459.2024.2366030

[13] A. R. Lundborg, I. Kim, R. D. Shah, R. J. Samworth, The projected covariance measure for assumption-lean variable significance testing, Ann. Stat., 52 (2024), 2851-2878. https://doi.org/10.1214/24-AOS2447

[14] B. D. Williamson, P. B. Gilbert, M. Carone, N. Simon, Nonparametric variable importance assessment using machine learning techniques, Biometrics, 77 (2021), 9-22. https://doi.org/10.1111/biom.13392

[15] B. Dai, X. Shen, W. Pan, Significance tests of feature relevance for a black-box learner, IEEE Trans. Neural Netw. Learn. Syst., 35 (2022), 1898-1911. https://doi.org/10.1109/TNNLS.2022.3185742

[16] B. D. Williamson, P. B. Gilbert, N. R. Simon, M. Carone, A general framework for inference on algorithm-agnostic variable importance, J. Am. Stat. Assoc., 118 (2023), 1645-1658. https://doi.org/10.1080/01621459.2021.2003200

[17] T. Lai, Z. Zhang, Y. Wang, L. Kong, Testing independence of functional variables by angle covariance, J. Multivar. Anal., 182 (2021), 104711. https://doi.org/10.1016/j.jmva.2020.104711

[18] Y. Zhou, Y. Zhang, L. Zhu, A projective approach to conditional independence test for dependent processes, J. Bus. Econ. Stat., 40 (2022), 398-407. https://doi.org/10.1080/07350015.2020.1826952

[19] F. Ferraty, A. Mas, P. Vieu, Nonparametric regression on functional data: inference and practical aspects, Aust. N. Z. J. Stat., 49 (2007), 267-286. https://doi.org/10.1111/j.1467-842X.2007.00480.x

[20] F. Ferraty, A. Laksaci, A. Tadj, P. Vieu, Kernel regression with functional response, Electron. J. Stat., 5 (2011), 159-171. https://doi.org/10.1214/11-EJS600

[21] Z. Jin, D. S. Matteson, Generalizing distance covariance to measure and test multivariate mutual dependence via complete and incomplete V-statistics, J. Multivar. Anal., 168 (2018), 304-322. https://doi.org/10.1016/j.jmva.2018.08.006

[22] F. Yao, H. G. Müller, J. L. Wang, Functional data analysis for sparse longitudinal data, J. Am. Stat. Assoc., 100 (2005), 577-590. https://doi.org/10.1198/016214504000001745

[23] R. Ghosal, A. Maity, T. Clark, S. B. Longo, Variable selection in functional linear concurrent regression, J. R. Stat. Soc. Ser. C Appl. Stat., 69 (2020), 565-587. https://doi.org/10.1111/rssc.12408

[24] N. Pfister, P. Bühlmann, B. Schölkopf, J. Peters, Kernel-based tests for joint independence, J. R. Stat. Soc. Ser. B Stat. Methodol., 80 (2017), 5-31. https://doi.org/10.1111/rssb.12235