论文检索

资产定价因子模型检验：样本外视角AI 解读

We develop the Sample Splitting Alpha (SSA) test, a formal out-of-sample (OOS) test for evaluating whether an asset pricing factor model satisfies the zero-alpha restriction in high-dimensional settings. The test uses sample splitting to separate portfolio weight estimation from model evaluation and ridge regularization to stabilize the portfolio problem when the number of test assets is large. We show that each single split SSA statistic is asymptotically Gaussian under…

高维线性因子定价模型的 Lq 范数 alpha 检验AI 解读

We consider testing zero pricing errors in high-dimensional linear factor pricing models. Existing methods are mainly based on either an $L_2$ statistic, which is effective under dense alternatives, or an $L_\infty$ statistic, which is powerful under very sparse alternatives. To bridge these two regimes, we develop a class of $L_q$-based tests for finite $q$, including the practically useful $L_4$ and $L_6$ cases. We show that larger $q$ leads to greater sensitivity to…

高维矩阵值时间序列的时空自回归模型AI 解读

Motivated by predicting intraday trading volume curves, we consider two spatio-temporal autoregressive models for matrix time series, in which each column may represent daily trading volume curve of one asset, and each row captures synchronized 5-minute volume intervals acrossmultiple assets. While traditional matrix time series focus mainly on temporal evolution, our approach incorporates both spatial and temporal dynamics, enabling simultaneous analysis of interactions…

面向重尾数据的高维切片逆 Kendall 秩相关估计AI 解读

Sufficient dimension reduction is an important branch of statistical learning, which performs an optimal projection of covariates under a supervised learning framework. Most of the existing sufficient dimension reduction algorithms require strict restrictions on the distribution of models, making them sensitive to heavy-tailed predictors and outliers. In this article, we propose a novel method called Sliced Inverse Kendall’s tau Estimation (SIKE) designed for analyzing…

具有社群网络结构的高维多变量已实现波动率预测AI 解读

We introduce the Community Network Heterogeneous Autoregressive model with Quarticity (CNHARQ), a novel framework that integrates network-based information to enhance the forecasting of multivariate realized volatilities. To address the curse of dimensionality, we propose a Correlation-Based Stochastic Block Model (CBSBM) to uncover latent community structures from the correlation network of realized volatilities of N assets. This approach reduces the number of unknown…

线性因子模型的 Alpha 检验：投资组合方法AI 解读

This paper develops a test for evaluating linear factor models in high-dimensional settings. The proposed Maximum Random Sparse Portfolio (MRSP) test generates L random sparse portfolios, each obtained through K random draws, and then selects the hardest-to-price portfolio to assess factor model performance. By evaluating multiple randomly generated sparse portfolios, the MRSP test retains a portfolio-based economic interpretation while avoiding reliance on a single…

多重门槛回归的 Lasso 后推断及收益可预测性应用AI 解读

This article revisits the multiple threshold regression model, wherein coefficient parameters shift across regimes in accordance with the value of a threshold variable. We focus on developing a post-Lasso inference framework to resolve the selection uncertainty—particularly pronounced when threshold effects are weak—intrinsic to the group Lasso-based procedure that jointly estimates the number and locations of multiple thresholds. This objective is accomplished by…

可观测因子与潜在因子AI 解读

We test for temporal stability in local linear projection coefficients of observable factors on latent ones embedded in a high-dimensional vector obeying a linear factor model. The proposed test explores the fact that, under the null hypothesis, residuals from global linear projections of observable factors on latent ones, computed over a fixed time interval via Principal Component Analysis (PCA), should also be locally uncorrelated with the PCA factors. The test is fully…

设定 LASSO 与灵活的特征型资产定价模型AI 解读

This paper studies a partially linear semiparametric additive model that allows for interactions among variables in high-dimensional settings. We propose the Specification LASSO (S-LASSO), a two-step method that integrates LASSO and Adaptive Group LASSO to simultaneously perform variable selection and model specification. Theoretically, we establish that S-LASSO possesses oracle properties in terms of selection consistency and asymptotic normality. Monte Carlo simulations…

用于企业生存预测的高维删失 MIDAS 逻辑回归AI 解读

This paper addresses the challenge of forecasting corporate distress, a problem marked by three key statistical hurdles: (i) right censoring, (ii) high-dimensional predictors, and (iii) mixed-frequency data. To overcome these complexities, we introduce a novel high-dimensional censored MIDAS (Mixed Data Sampling) logistic regression. Our approach handles censoring through inverse probability weighting and achieves accurate estimation with numerous mixed-frequency predictors…

预印本版本摘要 · 查看来源

共同基金 alpha 的异质可预测性：稀疏聚类 GMM 方法AI 解读

Mutual fund managers' skills, measured by risk-adjusted alphas, are predictable using fund characteristics identified by machine learning (e.g., Kaniel et al., 2023, JFE; DeMiguel et al., 2023, JFE). However, alpha's predictive power varies across funds and periods, with most funds exhibiting negligible alphas. To model this heterogeneous predictability, this paper introduces Sparse Clustering GMM, a nonparametric approach for uncovering latent fund groups. SCGMM clusters…

Lévy过程的快速无似然参数估计AI 解读

ABSTRACT Lévy processes are widely used in financial modeling due to their ability to capture discontinuities and heavy tails, which are common in high‐frequency asset return data. However, parameter estimation remains a challenge when associated likelihoods are unavailable or costly to compute. We propose a fast and accurate method for Lévy parameter estimation using the neural Bayes estimation (NBE) framework—a simulation‐based, likelihood‐free approach that leverages…

高维环境中的涵盖检验与递进检验AI 解读

This paper introduces the Subseries-based Cauchy Combination Test (SCT), a novel procedure for testing encompassing relationships or model validity using identification conditions formulated as multiple moment restrictions. SCT applies to weakly or short-range-dependent data and eliminates the need to estimate high-dimensional covariance matrices. Unlike Wald- or J-type tests, it remains reliable in both low- and high-dimensional settings. The test is asymptotically unbiased…

宏观审慎政策的尾部传导：叙事识别证据AI 解读

ABSTRACT We estimate the causal effects of macroprudential policies on the entire distribution of GDP growth for advanced European economies using a narrative‐identification strategy in a quantile‐regression framework. While macroprudential policy has near‐zero effects on the center of the GDP‐growth distribution, tighter policy brings benefits by reducing the variance of future growth, significantly boosting the left tail while simultaneously reducing the right. Assessing a…

广义自回归得分树与森林AI 解读

We propose methods to improve the forecasts from generalized autoregressive score (GAS) models (Creal, et al., 2013; Harvey, 2013) by localizing their parameters using decision trees and random forests. These methods avoid the curse of dimensionality faced by kernel-based approaches, and allow one to draw on information from multiple state variables simultaneously. We apply the new models to four distinct empirical analyses, and in all applications the proposed new methods…

动态矩阵因子模型：协变量驱动的时变载荷AI 解读

This paper proposes a covariate-driven matrix factor model in which the row and column loading matrices evolve as nonparametric functions of an observable time-varying covariate sequence. This flexible specification accommodates dynamic factor loadings driven by the temporal characteristics of the covariate. We develop a nonparametric estimation procedure that combines kernel smoothing with principal component analysis (PCA). Under high-dimensional asymptotics, we establish…

分位数中的区制特定股票收益可预测性AI 解读

This article captures the underlying regime switching mechanism in the prediction of stock returns via a predictive quantile regression with multiple thresholds. The predictability of each predictor is allowed to switch from one regime to another according to the value of a threshold variable and could vary across quantiles, and the predictors could possess heterogeneous degrees of persistence. Statistical learning techniques, including a sequential estimation procedure, an…

含影响节点与社群的高维分位数向量自回归AI 解读

Quantile vector autoregression (QVAR) models offer enhanced capabilities over vector autoregression (VAR) models in analyzing asymmetric interactions within multiple time series and are widely used in many areas, including finance and economics. However, in scenarios involving high-dimensional data where the number of time series N exceeds the length of the time series T, both parameter estimation and the theoretical establishment present significant challenges. Notably,…

高维极值图结构学习AI 解读

Extremal graphical models encode the conditional independence structure of multivariate extremes. Key statistics for learning extremal graphical structures are empirical extremal variograms, for which we prove non-asymptotic concentration bounds that hold under general domain of attraction conditions. For the popular class of Hüsler--Reiss models, we propose a majority voting algorithm for learning the underlying graph from data through $L^1$ regularized optimization. Our…

高维预测回归中的 LASSO 推断AI 解读

LASSO inflicts shrinkage bias on estimated coefficients, which undermines asymptotic normality and invalidates standard inferential procedures based on the t -statistic. Given cross sectional data, the desparsified LASSO has emerged as a well-known remedy for correcting the shrinkage bias. In the context of high dimensional predictive regression, the desparsified LASSO faces an additional challenge: the Stambaugh bias arising from nonstationary regressors modeled as local…

高维条件因子模型估计的统一框架AI 解读

This article presents a general framework for estimating high-dimensional conditional latent factor models via constrained nuclear norm regularization. We establish large sample properties of the estimators and provide efficient algorithms for their computation. To improve practical applicability, we propose a cross-validation procedure for selecting the regularization parameter. Our framework unifies the estimation of various conditional factor models, enabling the…

高维时间序列预测回归中有效协整秩的确定AI 解读

This article proposes a new approach to identifying the effective cointegration rank in high-dimensional unit-root (HDUR) time series from a prediction perspective using reduced-rank regression. For a HDUR process xt∈RN and a stationary series yt∈Rp of interest, our goal is to predict future values of yt using xt and lagged values of yt. The proposed framework consists of a two-step estimation procedure. First, the Principal Component Analysis is used to identify all…

GARCH-MIDAS 模型的自适应组 LASSOAI 解读

This article investigates the variable selection problem in the generalized autoregressive conditional heteroscedasticity-mixed-data sampling (GARCH-MIDAS) model of Engle, Ghysels, and Sohn (Citation2013), and establishes the corresponding theoretical properties along with a feasible computational algorithm. The proposed method is based on a penalized log-partial likelihood with an adaptively group-weighted L2 penalty on the long-term component coefficients. The variable…

含未观测异质性的大型面板多重结构突变估计AI 解读

This article proposes a novel algorithm to identify potentially multiple breaks in linear panel data models, while the slope coefficients can have individual heterogeneity and the cross-sectional dimension is allowed to diverge jointly with the time span. The algorithm adopts a shrinkage penalty to detect breaks, and delivers a consistent estimator for the number of breaks and fraction-consistent estimators for break dates. In the presence of latent grouped heterogeneity, we…