arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.23355stat.ME
收藏

基于似然作为数据的稳健模型选择

Robust model selection using likelihood as data

University of Connecticut(康涅狄格大学);Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院)

Jongwoo Choi, Neil A. Spencer, Jeffrey W. Miller

AI总结:

本文提出基于似然值建模的稳健模型选择方法,通过估计和量化似然值的期望来提供校准的推断,以应对设定错误情况下的模型选择问题。

摘要:

模型选择是统计学中的核心任务,但标准方法在设定错误的情况下缺乏鲁棒性,因为真实的数据生成过程(DGP)不在候选模型集合中。关键限制是现有方法——包括信息准则和贝叶斯后验——无法量化每个候选模型对真实DGP近似程度的不确定性。在本文中,我们提出了一种基于对似然值本身建模的新型模型选择方法。具体来说,给定K个候选模型和n个观测值,我们将n×K的负对数似然值矩阵视为一个随机数据矩阵,并观察到每行的期望值等于K个模型与真实DGP之间的Kullback-Leibler散度向量,加上一个加性常数。我们使用多元正态模型来估计并量化该期望值的不确定性,为在设定错误情况下的稳健模型选择提供校准的推断。该过程易于计算、可解释,并具有理论保证,包括一致性。

英文摘要:

Model selection is a central task in statistics, but standard methods are not robust in misspecified settings where the true data-generating process (DGP) is not in the set of candidate models. The key limitation is that existing methods -- including information criteria and Bayesian posteriors -- do not quantify uncertainty about how well each candidate model approximates the true DGP. In this paper, we introduce a novel approach to model selection based on modeling the likelihood values themselves. Specifically, given $K$ candidate models and $n$ observations, we view the $n\times K$ matrix of negative log-likelihood values as a random data matrix and observe that the expectation of each row is equal to the vector of Kullback--Leibler divergences between the $K$ models and the true DGP, up to an additive constant. We use a multivariate normal model to estimate and quantify uncertainty in this expectation, providing calibrated inferences for robust model selection under misspecification. The procedure is easy to compute, interpretable, and comes with theoretical guarantees, including consistency.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑