Dynamic Latent-Factor Model with High-Dimensional Asset Characteristics

TL;DR

This paper introduces a new estimation method for a dynamic latent-factor model with many asset characteristics, demonstrating its effectiveness in crypto asset pricing and risk premium measurement.

Contribution

The paper develops a novel estimation procedure using Double Selection Lasso for high-dimensional asset characteristics in a dynamic latent-factor model, with valid inference capabilities.

Findings

The estimator shows strong out-of-sample pricing performance.

Crypto assets exhibit positive risk premiums for inflation-mimicking portfolios.

The method effectively handles high-dimensional data with asymptotic validity.

Abstract

We develop novel estimation procedures with supporting econometric theory for a dynamic latent-factor model with high-dimensional asset characteristics, that is, the number of characteristics is on the order of the sample size. Utilizing the Double Selection Lasso estimator, our procedure employs regularization to eliminate characteristics with low signal-to-noise ratios yet maintains asymptotically valid inference for asset pricing tests. The crypto asset class is well-suited for applying this model given the limited number of tradable assets and years of data as well as the rich set of available asset characteristics. The empirical results present out-of-sample pricing abilities and risk-adjusted returns for our novel estimator as compared to benchmark methods. We provide an inference procedure for measuring the risk premium of an observable nontradable factor, and employ this to find that the inflation-mimicking portfolio in the crypto asset class has positive risk compensation.