Hierarchical Time-Varying Estimation of Asset Pricing Models

Richard T. Baillie*, Fabio Calonaci, George Kapetanios

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

This paper presents a new hierarchical methodology for estimating multi factor dynamic asset pricing models. The approach is loosely based on the sequential Fama–MacBeth approach and developed in a kernel regression framework. However, the methodology uses a very flexible bandwidth selection method which is able to emphasize recent data and information to derive the most appropriate estimates of risk premia and factor loadings at each point in time. The choice of bandwidths and weighting schemes are achieved by a cross-validation procedure; this leads to consistent estimators of the risk premia and factor loadings. Additionally, an out-of-sample forecasting exercise indicates that the hierarchical method leads to a statistically significant improvement in forecast loss function measures, independently of the type of factor considered.

Original languageEnglish
Article number14
JournalJournal of Risk and Financial Management
Volume15
Issue number1
DOIs
Publication statusPublished - Jan 2022

Keywords

  • asset pricing model
  • cross-validation
  • estimation of beta
  • Fama–MacBeth model
  • kernel-weighted regressions
  • time-varying parameter regressions

Fingerprint

Dive into the research topics of 'Hierarchical Time-Varying Estimation of Asset Pricing Models'. Together they form a unique fingerprint.

Cite this