学术讲座:高维情况下的相关结构

题目:Estimation of a Multiplicative Correlation Stracture in the Large Dimensional Case
报告人:Oliver Linton
报告时间:2018年11月13日(周二) 13:30 pm
地点:国际经管学院会议室(诚明楼三层)
主办方:国际经济管理学院


摘要:We propose a Kronecker product model for correlation or covariance matrices in the large dimension case. The number of parameters of the model increases logarithmically with the dimension of the matrix. We propose a minimum distance (MD) estimator based on a log-linear property of the model, as well as a one-step estimator, which is a one-step approximation to the quasi-maximum likelihood estimator (QMLE). We establish the rate of convergence and a central limit theorem (CLT) for our estimators in the large dimensional case. A specification test and tools for Kronecker product model selection and inference are provided. In an Monte Carlo study where a Kronecker product model is correctly specified, our estimators exhibit superior performance. In an empirical application to portfolio choice for S&P500 daily returns, we demonstrate that certain Kronecker product models are good approximations to the general covariance matrix.

摘要:我们为高维情况下的相关或协方差矩阵提出了 Kronecker 乘积模型。 模型的参数数量随矩阵的维数呈对数增加。 我们提出了一个基于模型的对数线性属性的最小距离 (MD) 估计参数,以及一个一步估计参数,它是准最大似然估计参数 (QMLE) 的一步近似。 我们在高维情况下为我们的估计器建立了收敛速度和中心极限定理 (CLT)。 提供了用于 Kronecker 乘积模型选择和推理的规范测试和工具。 在正确指定 Kronecker 乘积模型的蒙特卡洛研究中,我们的估计器表现出卓越的性能。  S&P500 每日回报的投资组合选择的实证应用中,我们证明某些 Kronecker 乘积模型很好地近似于一般协方差矩阵。