Estimation of Sparsity-Induced Weak Factor Models
Estimation of Sparsity-Induced Weak Factor Models
复制标题
稀疏性引发的弱因子模型的估计
DOI：
10.1080/07350015.2021.2008405
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Yamagata Takashi
中科院分区：
文献类型：
--
作者：
Uematsu Yoshimasa;Yamagata Takashi
本文研究了具有较大截面和时间序列维度(分别为NandT)的稀疏诱导弱因素(SWF)模型的估计问题。它假定数据协方差矩阵的第k个最大特征值与未知指数成比例增长。采用相同旋转的主成分(PC)估计量，增长率αk与第k个因子负荷的稀疏程度有关。这比最近的因子模型上的典型假设要弱得多，在这些模型中，所有最大的特征值都成比例地发散。我们应用了Uematsu等人的稀疏正交因子回归(SFARR)方法。对SWF模型进行估计，得出估计误差界。重要的是，我们的方法还得到了αk的一致估计。有限样本实验表明，新估计量的性能一致地优于PC估计量。我们将我们的方法应用于债券收益率的预测，结果表明，我们的方法比基于PC的方法要好。我们还分析了S&P500公司的证券收益，发现第一个因素一致接近于强，而其他因素都很弱。
This article investigates estimation of sparsity-induced weak factor (sWF) models, with large cross-sectional and time-series dimensions (NandT, respectively). It assumes that thekth largest eigenvalue of a data covariance matrix grows proportionally towith unknown exponentsfor. Employing the same rotation of the principal components (PC) estimator, the growth rateαkis linked to the degree of sparsity ofkth factor loadings. This is much weaker than the typical assumption on the recent factor models, in which all therlargest eigenvalues diverge proportionally toN. We apply the method of sparse orthogonal factor regression (SOFAR) by Uematsu et al. to estimate the sWF models and derive the estimation error bound. Importantly, our method also yields consistent estimation ofαk. A finite sample experiment shows that the performance of the new estimator uniformly dominates that of the PC estimator. We apply our method to forecasting bond yields and the results demonstrate that our method outperforms that based on the PC. We also analyze S&P500 firm security returns and find that the first factor is consistently near strong while the others are weak.