New Approaches to Robust Inference on Market (Non-)Efficiency, Volatility Clustering and Nonlinear Dependence

TL;DR

This paper introduces robust methods for analyzing market efficiency, volatility clustering, and nonlinear dependence in financial data, addressing issues caused by heavy tails and heterogeneity that challenge traditional techniques.

Contribution

It proposes new measures based on powers of absolute returns and signed versions, along with robust $t$-statistics tests for valid inference in complex financial time series.

Findings

Robust inference methods outperform traditional ones in heterogenous data.

New measures effectively capture nonlinear dependence and volatility clustering.

Empirical results demonstrate the methods' wide applicability and advantages.

Abstract

Many financial and economic variables, including financial returns, exhibit nonlinear dependence, heterogeneity and heavy-tailedness. These properties may make problematic the analysis of (non-)efficiency and volatility clustering in economic and financial markets using traditional approaches that appeal to asymptotic normality of sample autocorrelation functions of returns and their squares. This paper presents new approaches to deal with the above problems. We provide the results that motivate the use of measures of market (non-)efficiency and volatility clustering based on (small) powers of absolute returns and their signed versions. We further provide new approaches to robust inference on the measures in the case of general time series, including GARCH-type processes. The approaches are based on robust $t-$statistics tests and new results on their applicability are presented. In the approaches, parameter estimates (e.g., estimates of measures of nonlinear dependence) are computed for groups of data, and the inference is based on $t-$statistics in the resulting group estimates. This results in valid robust inference under heterogeneity and dependence assumptions satisfied in real-world financial markets. Numerical results and empirical applications confirm the advantages and wide applicability of the proposed approaches.