Single-step and multiple-step forecasting in one-dimensional single chirp signal using MCMC-based Bayesian analysis

ABSTRACT

Chirp signals are frequently used in different areas of science and engineering. MCMC-based Bayesian inference is done here for the purpose of one-step and multiple-step prediction in the case of the one-dimensional single chirp signal with iid error structure as well as dependent error structure with exponentially decaying covariances. We use Gibbs sampling technique and random walk MCMC to update the parameters. We perform total five simulation studies for the illustration purpose. We also do some real-data analysis to show how the method is working in practice.

KEYWORDS:

• Bayesian inference
• Chirp signal
• Gibbs Sampling
• Posterior predictive density
• Random walk MCMC

MATHEMATICS SUBJECT CLASSIFICATION:

• Primary 62
• Secondary 62F15

Acknowledgments

The author is very grateful to Moumita Das for her insightful comments and suggestions which improve the article in every aspect. The author is also grateful to the assistance obtained from uci machine learning data repository (http://archive.ics.uci.edu/ml) for the real datasets. The author also cordially thanks two anonymous referees for their very valuable and important comments which help to improve the previous manuscript thoroughly.