High-dimensional test for alpha in linear factor pricing models with sparse alternatives

Feng, Long; Lan, Wei; Liu, Binghui

doi:10.1016/j.jeconom.2021.07.011

Cited by 11 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the sparse alternatives, that is, the number of non‐zero alphas are very small, a max‐type test is preferred, such as Feng et al (2022). However, the max‐type test proposed in Feng et al (2022) performs not very well under the heavy‐tailed distributions. So how to construct a robust spatial‐sign‐based max‐type test for testing the high‐dimensional alpha deserves some further studies.…”

Section: Discussionmentioning

confidence: 99%

“…The above class of weighted spatial‐sign tests are sum‐type tests, which performs very well under the dense alternatives, that is, the number of non‐zero alphas are large. For the sparse alternatives, that is, the number of non‐zero alphas are very small, a max‐type test is preferred, such as Feng et al (2022). However, the max‐type test proposed in Feng et al (2022) performs not very well under the heavy‐tailed distributions.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

High‐dimensional non‐parametric tests for linear asset pricing models

Zhao

Chen

2022

Stat

View full text Add to dashboard Cite

This paper develops a novel non‐parametric test for testing the high‐dimensional alpha in linear asset pricing models, where the number of securities can be much larger than the time‐dimension of the return series. The asymptotic null distribution and the local power property are established for a class of weighted spatial‐sign tests, which results in an optimal test INST by choosing the weight function as the inverse of the norm. The INST test is optimal in the sense that it is locally most powerful within this class. As a non‐parametric test, the INST test is also robust to the departures from normality of the error distribution. Monte Carlo simulation and empirical study with real financial data show the superiority of INST test in terms of both robustness and efficiency.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

High‐dimensional non‐parametric tests for linear asset pricing models

Zhao

Chen

2022

Stat

View full text Add to dashboard Cite

show abstract

“…Although the GRS test is commonly used to address the above mentioned question, it has certain limitations. First, the GRS type test is only applicable when the number of assets N is fixed and much less than the number of observations T (e.g., Pesaran and Yamagata, 2017;Lan et al, 2018;Feng et al, 2022). This limitation arises from the inconsistency and nontrivial bias introduced by the sample covariance matrix estimator when N > T (Bai and Silverstein, 2005).…”

Section: Introductionmentioning

confidence: 99%

“…However, the HDA test is constrained by sparse alternatives, resolving only the first two limitations. To tackle the third limitation,Fan et al (2015) introduced a power enhancement screening procedure for increased test power against sparse alternatives, applicable to high-dimensional test assets Feng et al (2022). developed a max-of-squares-type test to assess the mean-variance efficiency.…”

mentioning

confidence: 99%

Maximum Conditional Alpha Test for Conditional Multi-Factor Models

Zhang,

Lan,

Fan

et al. 2025

STAT SINICA

View full text Add to dashboard Cite

In this paper, a novel test, called the maximum conditional alpha (MCA) test, which enhances the testing power for detecting alpha in linear multi-factor models, is proposed. This test is specifically designed for conditional multi-factor models with time-varying coefficients, where the number of test assets (N ) exceeds the number of observations (T ) and the alternative hypothesis is a sparse vector, meaning that only a few components violate the null hypothesis.By carefully studying the estimation error derived from the B-spline estimation, we rigorously demonstrate that the proposed test converges to a type-I extreme value distribution when min(T, N ) tends to infinity, subject to mild conditions. Furthermore, the proposed MCA test was extended to incorporate latent factors within conditional multi-factor models. The small-sample properties of the

show abstract

“…Ma, Lan, Su, and Tsai (2020) employ polynomial spline techniques to allow for time variations in factor loadings when testing for alphas. Feng, Lan, Liu, and Ma (2022) propose a max-of-square type test of the intercepts instead of the average used in the literature, and recommend using a combination of the two testing procedures. He, He, Huang, and Zhou (2022) propose two statistics, a Wald type statistic which require n and T to be of the same order of magnitude and a standardised t-ratio.…”

Section: Introductionmentioning

confidence: 99%