Backend
Adaptive Tests of Pricing Restrictions with Observed and Latent Factors
arXiv stat.TH0 views
arXiv:2611.25549v1 Announce Type: cross Abstract: This paper develops a high-dimensional test for asset pricing models with observed and latent factors. The null hypothesis allows the intercepts from an observed-factor regression to be nonzero, provided that they lie in the latent factor loading space. We estimate the pricing errors in three steps: regress returns on the observed factors, extract latent factors from the lagged covariance structure of the regression residuals, and regress returns on both observed and estimated latent factors. The intercept from the final regression serves as the estimated pricing error. We construct Sum and Max tests based on the estimated pricing errors to detect diffuse and concentrated alternatives, respectively, and combine them using a Cauchy procedure. Under suitable regularity conditions, we establish the joint null distribution of the component statistics, their asymptotic independence, and their power against alternative hypotheses. We also propose a residual bootstrap and establish its first-order validity. Simulation studies examine the finite-sample performance of the tests under different pricing-error patterns and factor-number choices. An application to S\&P 500 stocks illustrates the use of the proposed framework in evaluating an observed-factor pricing model after latent-factor adjustment.
Source:https://arxiv.org/abs/2611.25549PreviousDifferentially Private Score Estimation with Applications to Score-Based Generative ModelsNextA note on the learning coefficient of exceptional singularities
Related posts
Splunk's Empty Cluster Secret Turns a Standalone Default into an Authentication Bypass
0dev.to
Pragmatic zero-trust: what to ship in the first 90 days
0dev.to
The EKS cost playbook: 7 levers we pull on every audit
0dev.to
Building a hearing test in the browser with the Web Audio API (and why we refuse to call it an audiogram)
0dev.to
How we score French speaking with AI: an honest look at limits
0dev.to
What a Four-Letter Word Ladder Taught Me About Planning Under Constraints
0dev.to