Scholarlink

<p>This paper establishes identifiability results for mixture regression models with skew-normal errors under both fixed and random designs. We propose a novel penalized maximum likelihood estimation method for such models and demonstrate the strong consistency of the proposed estimator. An EM-type algorithm is developed to derive the penalized estimator. The finite sample properties of the proposed methodology are examined using extensive simulations, and a real data example is presented for illustration.</p>

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 penalized likelihood estimation for mixture regressions with skew-normal errors

  • 期刊论文

  • 发表日期：

    2025年8月22日

查看全文
  • Libin Jin,
  • Shuyan Chen,
  • Xiaowen Dai,
  • Lei Shi

摘要

This paper establishes identifiability results for mixture regression models with skew-normal errors under both fixed and random designs. We propose a novel penalized maximum likelihood estimation method for such models and demonstrate the strong consistency of the proposed estimator. An EM-type algorithm is developed to derive the penalized estimator. The finite sample properties of the proposed methodology are examined using extensive simulations, and a real data example is presented for illustration.