CMStatistics 2022: Start Registration
View Submission - CFE
Title: Exact likelihood for inverse gamma stochastic volatility models Authors:  Blessings Majoni - National graduate institute for policy studies (Japan) [presenting]
Roberto Leon-Gonzalez - GRIPS (Japan)
Abstract: A novel closed-form solution of the likelihood for the inverse gamma stochastic volatility (SV) model is obtained. It is shown that by marginalizing out the volatilities, the model that we obtain has the resemblance of a GARCH in the sense that the formulas that we get are similar, which simplifies computations significantly and permits maximum likelihood estimation. Recent literature has also attempted to obtain SV models that are as simple as the GARCH for computational efficiency. However, the literature has only obtained this solution for gamma SV models and for restricted non-stationary models. We provide two empirical applications, one to UK exchange rate data and another to UK inflation data. We find that our proposed model has a better empirical fit than previously proposed models.