Investigation shows strong global consistency in probability density function estimation, suggesting reliable applications in data analysis.
Key Points
Strong global consistency achieved in the multivariate associated kernel estimators, ensuring reliable density function estimation.
Pointwise asymptotic normality confirms the robustness of the nonparametric estimator across various distribution types.
Analysis uses recursive estimators within the framework of associated kernels, enhancing estimation capabilities for diverse data forms, including categorical and discrete distributions. The study revisits illustrative examples to demonstrate the application of these estimators.