A Bayesian analysis of gain-loss asymmetry

TL;DR

This paper introduces a Bayesian method to analyze gain-loss asymmetry in financial time series, relaxing normality assumptions and assessing robustness through sensitivity analysis.

Contribution

It presents a Bayesian generalization of the t-Test for gain-loss asymmetry, compares two data distribution models, and evaluates the method's convergence and robustness.

Findings

Bayesian approach effectively detects asymmetry.

Results are robust across different models.

Graphical analysis illustrates asymmetry significance.

Abstract

We perform a quantitative analysis of the gain/loss asymmetry for financial time series by using a Bayesian approach. In particular, we focus on some selected indices and analyze the statistical significance of the asymmetry amount through a Bayesian generalization of the t-Test, which relaxes the normality assumption on the underlying distribution. We propose two different models for data distribution, we study the convergence of our method and we provide several graphical representations of our numerical results. Finally, we perform a sensitivity analysis with respect to model parameters in order to study the reliability and robustness of our results.