regspec-package: Non-parametric multirate spectral density estimation via...

In regspec: Non-Parametric Bayesian Spectrum Estimation for Multirate Data

Non-parametric multirate spectral density estimation via linear Bayes.

Description

Estimate a spectral density function of a stationary time series. Produces a linear Bayes estimate with credible intervals. Can incorporate time series data from multiple realizations with different sampling rate. Can deal with time series data that has been filtered with a known filter (e.g. quarterly totals from monthly values).

Details

Currently, the package's centrepiece is the function regspec, which implements spectral density estimation from time series data at integer time points. A novel element of the code is it's ability to assimilate subsampled and filtered data.

The package's data files, which will be loaded automatically, include synthetic and real examples of time series data that feature in the Examples sections of the functions' help files.

Author(s)

Ben Powell

References

Nason, G.P., Powell, B., Elliott, D. and Smith, P. (2016) Should We Sample a Time Series More Frequently? Decision Support via Multirate Spectrum Estimation. Journal of the Royal Statistical Society, Series A., 179, (to appear).

See Also

regspec

regspec documentation built on Sept. 20, 2023, 5:07 p.m.