Strong consistency for heteroscedastic semiparametric errors-in-variables models with dependent errors
This article focuses on the strong consistency properties of a class of heteroscedastic semiparametric errors-in-variables models with dependent measurement errors and dependent random errors. The dependence structure is specified in a fairly general manner, allowing for a broad range of temporal dependence encountered in practical applications. Under mild regularity conditions, strong consistency of the proposed estimators is established for both the parametric and nonparametric components. Numerical simulations are provided to illustrate the finite-sample convergence behavior of the estimators and to support the theoretical results. In addition, an empirical analysis using daily financial data demonstrates the practical applicability of the proposed model. The results extend existing consistency theory for semiparametric errors-in-variables models to dependent settings and offer a theoretical basis for future asymptotic and inferential studies.
Authors
- Jingjun Guo
- Feng Xu (ORCID: https://orcid.org/0000-0003-3818-0468)
- Xiaoqin Deng
Institutions
- Guilin University of Technology (CN)
- Lanzhou University of Finance and Economics (CN)
Publication Details
- Journal
- Communication in Statistics- Theory and Methods
- Published
- 2026-11-16
- DOI
- https://doi.org/10.1080/03610926.2026.2759304
- Primary Topic
- Statistical Methods and Inference
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China