In this paper, we suggest an empirical Bayes-type prior for the model space in Bayesian model averaging (BMA) in a method we call tuned Bayesian model averaging (tBMA). This method relies on leave-one-out cross validation to choose a hyper-parameter that will cause the averaging process to favor either smaller or richer models in the prior distribution over the models. We find that this method ...

We study the decidability and expressiveness issues of µ-calculus on data words and data ω-words. It is shown that the full logic as well as the fragment which uses only the least fixpoints are undecidable, while the fragment containing only greatest fixpoints is decidable. Two subclasses, namely BMA and BR, obtained by limiting the compositions of formulas and their automata characterizations ...

Empirical growth research faces a high degree of model uncertainty. The current paper deals with the fundamental issue of parameter estimation under model uncertainty, and compares the performance of various model averaging techniques. In particular, it contrasts Bayesian model averaging (BMA) — currently one of the standard methods used in growth empirics — with a new method called weighted-av...

A new method, referred to as Bayesian Morphometry Algorithm (BMA), is presented, for morphology-function analysis of population-based medical imaging studies. In this paper, we apply BMA to a set of cross-sectional magnetic resonance images of subjects in the Baltimore Longitudinal Study of Aging, some of whom have very mild cognitive impairment, to demonstrate the algorithm's utility for deter...

Modifications to BMA K850 centrifugals permitted increased throughputs of "C" massecuite in the order of 100%. The resultant molasses purities were little affected, but brixes were two degrees lower than before modification. Tests showed that the prototype BMA KllOO can handle four tons of "C" massecuite per hour with molasses purities comparable with those of standard centrifugals, but with br...