Abstract

This talk pertains to a class of non-parametric methods for studying the misrepresentation issue in insurance applications. For this purpose, mixture models based on quantile regression in reproducing kernel Hilbert spaces are employed. Compared to the existing parametric approaches, the proposed framework features a more flexible statistics structure which could alleviate the risk of model misspecification, and is in the meantime more robust to outliers in the data. The proposed framework can not only estimate the prevalence of misrepresentation in the data, but also help identify the most suspicious individuals for the validation purpose. Through embedding state-of-the-art machine learning techniques, we present a novel statistics procedure to efficiently estimate the proposed misrepresentation model in the presence of massive data. The proposed methodology is applied to study the Medical Expenditure Panel Survey (MEPS) data, and a significant degree of misrepresentation activities are found on the self-reported insurance status.