Dataset Information

Power Enhancement in High Dimensional Cross-Sectional Tests.

ABSTRACT: We propose a novel technique to boost the power of testing a high-dimensional vector H : ? = 0 against sparse alternatives where the null hypothesis is violated only by a couple of components. Existing tests based on quadratic forms such as the Wald statistic often suffer from low powers due to the accumulation of errors in estimating high-dimensional parameters. More powerful tests for sparse alternatives such as thresholding and extreme-value tests, on the other hand, require either stringent conditions or bootstrap to derive the null distribution and often suffer from size distortions due to the slow convergence. Based on a screening technique, we introduce a "power enhancement component", which is zero under the null hypothesis with high probability, but diverges quickly under sparse alternatives. The proposed test statistic combines the power enhancement component with an asymptotically pivotal statistic, and strengthens the power under sparse alternatives. The null distribution does not require stringent regularity conditions, and is completely determined by that of the pivotal statistic. As specific applications, the proposed methods are applied to testing the factor pricing models and validating the cross-sectional independence in panel data models.

SUBMITTER: Fan J

PROVIDER: S-EPMC4714420 | biostudies-literature | 2015 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Power Enhancement in High Dimensional Cross-Sectional Tests.

Fan Jianqing J Liao Yuan Y Yao Jiawei J

Econometrica : journal of the Econometric Society 20150701 4

We propose a novel technique to boost the power of testing a high-dimensional vector H : θ = 0 against sparse alternatives where the null hypothesis is violated only by a couple of components. Existing tests based on quadratic forms such as the Wald statistic often suffer from low powers due to the accumulation of errors in estimating high-dimensional parameters. More powerful tests for sparse alternatives such as thresholding and extreme-value tests, on the other hand, requ ...[more]

PMID: 26778846

Similar Datasets

Project description:BackgroundIntracranial aneurysms and intracranial atherosclerosis are prevalent cerebrovascular diseases, and individuals with atherosclerosis have a higher incidence of aneurysms than those without atherosclerosis. However, few studies have conducted combined analyses to investigate the potential association between intracranial aneurysms and intracranial atherosclerosis. This retrospective cross-sectional study aimed to investigate the association between the characteristics of the aneurysm wall and intracranial large arterial plaque using high-resolution vessel wall imaging (HR-VWI).MethodsHospitalized patients diagnosed with anterior circulation unruptured intracranial aneurysms (UIAs), who were diagnosed at Huashan Hospital of Fudan University in Shanghai, China, between March 2016 to February 2018, were consecutively recruited for this study. The patients' pre-treatment HR-VWI images and 3D time-of-flight magnetic resonance angiography (3D-TOF-MRA) images were collected. The patients and UIAs were divided into two groups according to the presence or absence of plaque in the M1 segment of the middle cerebral artery (MCA). Clinical information and aneurysm characteristics were compared between the two groups. Aneurysm wall enhancement (AWE) and M1 plaque were graded on scales of 0 to 2 on HR-VWI. Based on the gradings, the correlation between AWE and the M1 plaques was analyzed.ResultsA total of 109 patients with 128 saccular UIAs in the anterior circulation were enrolled in the study. Of the patients, there were 56 patients (with 65 UIAs) in the group with M1 plaque and 53 patients (with 63 UIAs) in the group without plaque. There were significant differences between the two groups in terms of both their clinical information (age and hypertension) and aneurysm characteristics (AWE pattern and AWE degree). The grades of the AWE patterns and the AWE degrees of the UIAs were higher in the group with M1 plaque than in the group without plaque. In the M1 plaque group, the grade of M1 plaque was positively correlated with the grade of AWE pattern (correlation coefficient R=0.41, P=0.001) and the grade of AWE degree (correlation coefficient R=0.50, P<0.001).ConclusionsMCA atherosclerosis plaque was associated with the AWE of saccular aneurysms. When evaluating UIAs, attention should also be paid to the large arterial wall, which may assist in assessing the stability of the aneurysm and enable better decision making.

Dataset Information

Power Enhancement in High Dimensional Cross-Sectional Tests.

Publications

Power Enhancement in High Dimensional Cross-Sectional Tests.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets