Scholarlink

In this paper we propose a stategy to deal with outliers and nonlinearities in mortality rates in order to improve the predictive capacity of the LC model. In particular we use the singular value decomposition based on density power divergence to account for outliers and auto-regressive neural networks to handle nonlinearities. Empirical evidence on real data shows a significant improvement contribution of the proposed methodology.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Robust Non Linear Lee-Carter Type Model for Mortality Rate

  • 章节

  • 发表日期：

    2026年

查看全文
  • Michele La Rocca,
  • Cira Perna,
  • Marilena Sibillo

摘要

In this paper we propose a stategy to deal with outliers and nonlinearities in mortality rates in order to improve the predictive capacity of the LC model. In particular we use the singular value decomposition based on density power divergence to account for outliers and auto-regressive neural networks to handle nonlinearities. Empirical evidence on real data shows a significant improvement contribution of the proposed methodology.