Residual likelihood approach for asymmetric price relationship selection

Abstract

This study considers the problem of asymmetric price transmission model selection and investigates the performance of the recently developed model selection criteria (RIC) against commonly used alternatives (AIC and BIC) in terms of their ability to recover the true asymmetric data generating process. Asymmetric price transmission models are estimated and compared using the selection criteria. Monte Carlo simulation results indicate that the performance of the model selection methods depends on the sample size, the level of asymmetry and the amount of noise in the model used in the application. In larger samples, RIC is comparable to BIC and outperforms AIC. At higher noise levels, RIC is comparable to AIC and outperforms BIC. Additionally, at strong levels of asymmetry, RIC outperforms both AIC and BIC. These results suggest that RIC which has both BIC’s useful property of consistency and efficient property of AIC is a very reliable and useful criterion in asymmetric price transmission model selection.

Keywords

• Price Asymmetry
• Akaike’s Information Criteria
• Bayesian Information Criteria
• Residual Information Criteria
• residual likelihood
• Monte Carlo Simulation
• model selection