METROPOLIS MONTE-CARLO IMPLEMENTATION OF BAYESIAN TIME-DOMAIN PARAMETER-ESTIMATION - APPLICATION TO COUPLING-CONSTANT ESTIMATION FROM ANTIPHASE MULTIPLETS

The Bayesian perspective on statistics asserts that it makes sense to speak of a probability of an unknown parameter having a particular val ue. Given a model for an observed, noise-corrupted signal, we may use Bayesian methods to estimate not only the most probable value for each parameter but also their distributions. We present an implementation of the Bayesian parameter estimation formalism developed by G. L. Bret thorst (1990, J. Magn. Reson. 88, 533) using the Metropolis Monte Carl o sampling algorithm to perform the parameter and error estimation. Th is allows us to make very few assumptions about the shape of the poste rior distribution, and allows the easy introduction of prior knowledge about constraints among the model parameters. We present evidence tha t the error estimates obtained in this manner are realistic, and that the Monte Carlo approach can be used to accurately estimate coupling c onstants from antiphase doublets in synthetic and experimental data. ( C) 1998 Academic Press.