diag_geweke: Geweke Convergence diagnostics

In joergrieger/bvar: Estimation and forecasting of bayesian VAR models

Description

Geweke Convergence diagnostics

Usage

diag_geweke(obj, frac1, frac2, ...)

## S3 method for class 'bvar'
diag_geweke(obj, frac1, frac2, ...)

Arguments

obj	an estimated bvar model
frac1	first fraction
frac2	second fraction
...	not used

Details

Estimate convergence diagnostics of the mcmc sampler as in Geweke (1992). The diagnostics split the sample into two subsample, frac1 and frac2, and compares the mean and variance of these two subsample

z=\frac{\hat{θ}_1-\hat{θ}_2}{√{Var(\hatθ_1)+Var(\hatθ_2)}}

with θ_1 and θ_2 being the means of the coefficients of the two subsamples. The variance of the coefficients of the subsample are estimated using a spectral approach to adjust for the dependence between the two subsamples. This function uses the univariate version of the test in the sense that it performs a univariate test for each coefficient and calculates the probability that a coefficient has converged.

Value

returns a matrix with test results for each coefficient.

References

Geweke, John, Evaluating the Accuracy of Sampling-Based approaches to the Calculation of Posterior Moments, In: J.M. Bernardo, J.O. Berger, A. P. Dawid and A.F.M. Smith, Eds., Bayesian Statistics, Vol. 4, Clarendon Press, Oxford, 1992, pp. 169-183

joergrieger/bvar documentation built on July 3, 2020, 5:34 p.m.