Skip to content
All library documents

A Gaussian and Student’s t Mixture Autoregressive Model for Interest Rates

Article arXiv papers · Author: Savi Virolainen

Summary

The paper introduces a mixture autoregressive model whose components use both Gaussian and Student’s t distributions. This combination is designed to represent time series that switch between regimes with different variance behavior: some regimes are conditionally homoscedastic and Gaussian, while others are conditionally heteroscedastic and Student’s t. The model therefore allows a wider range of regime behavior than relying on either component type alone.

The authors demonstrate the model in an empirical application to the monthly U.S. spread between the three-month Treasury bill rate and the effective federal funds rate. The description says the model’s usefulness is demonstrated, but supplies no numerical comparison, forecast evaluation, or details of the fitted regimes. The evidence is thus confined to the stated application, and the summary does not establish how the model performs on other financial series or relative to alternative specifications.

Key ideas

  • The proposed autoregressive model combines Gaussian and Student’s t mixture components.
  • Gaussian components represent conditionally homoscedastic regimes, while Student’s t components allow conditional heteroscedasticity.
  • The model is applied to a monthly U.S. short-term interest rate spread.
  • The available description provides no comparative performance statistics or evidence beyond that application.

Tags

Full text
# A mixture autoregressive model based on Gaussian and Student's $t$-distributions


# A mixture autoregressive model based on Gaussian and Student's $t$-distributions









We introduce a new mixture autoregressive model which combines Gaussian and Student's $t$ mixture components. The model has very attractive properties analogous to the Gaussian and Student's $t$ mixture autoregressive models, but it is more flexible as it enables to model series which consist of both conditionally homoscedastic Gaussian regimes and conditionally heteroscedastic Student's $t$ regimes. The usefulness of our model is demonstrated in an empirical application to the monthly U.S. interest rate spread between the 3-month Treasury bill rate and the effective federal funds rate.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.