Variance estimation for multivariate dynamic linear models

Article Abstract:

The estimation of unknown variances in multivariate dynamic linear models is discussed. The method uses approximate conjugate analyses based on simple analytic approximation. The procedure was compared with a method based on the Robust filter. Results showed that the method is applicable to the sub-class of conjugate models. In addition, its one-step forecast errors were similar to those of the original method. The new method showed improvements in analyzing variances over the previous methods.

Models, Multivariate analysis

---

Bayes linear variance adjustment for locally linear DLMs

Article Abstract:

Proper variance specifications are vital to the performance of dynamic linear models (DLMs). Nonetheless, right specifications for other variance components are equally essential. The Bayes linear variance adjustment is used on locally linear DLMs to exhibit quadratic results of linear combinations of observables.

---

Bias in the estimation of non-linear transformation of the integrated variance of returns

Article Abstract:

An analytical approximation for the unconditional bias of estimators of non-linear transformations of integrated variance is derived.

United Kingdom, Science & research

Similar abstracts:

• Abstracts: Covariance estimation for multivariate conditionally Gaussian dynamic linear models. Evaluating the forecast densities of linear and non-linear models: applications to output growth and unemployment
• Abstracts: Differential interpretation of information in inflation forecasts. The role of commodity prices in formulating monetary policy
• Abstracts: Inflation and wage indexation in the postwar United States. Inflationary expectations and price setting behavior
• Abstracts: Risk attitudes and decision weights. A definition of subjective probabilities with state-dependent preferences
• Abstracts: A two-sector overlapping-generations model: a global characterization of the dynamical system. part 2 Sufficient conditions for inessentiality

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.