We deal with Bayesian inference for Beta autoregressive processes. We restrict our attention to the class of conditionally linear processes. These processes are particularly suitable for forecasting purposes, but are difficult to estimate due to the constraints on the parameter space. We provide a full Bayesian approach to the estimation and include the parameter restrictions in the inference p...

Decision making in light of uncertain and incomplete knowledge is one of the central themes in statistics and machine learning. Probabilistic Bayesian models provide a mathematically rigorous framework to formalise the data acquisition process while making explicit all relevant prior knowledge and assumptions. The resulting posterior distribution represents the state of knowledge of the model a...

Geostatistical analyses were first developed in the 1950's as a result of interest in areal or block averages for ore reserves in the mining industry. Today, variogram estimation and spatial prediction (kriging) span all sciences where data exhibit spatial correlation. Theoretical properties of the spatial process are addressed under the distribution-free and likelihood-based perspectives. Stre...

Conventional geostatistical methodology solves the problem of predicting the realized value of a linear functional of a Gaussian spatial stochastic process S…x) based on observations Yi ˆ S…xi † ‡ Zi at sampling locations xi , where the Zi are mutually independent, zero-mean Gaussian random variables. We describe two spatial applications for which Gaussian distributional assumptions are clearly...

Reliable prediction of subsurface flow and contaminant transport depends on the accuracy with which the values and spatial distribution of process-relevant model parameters can be identified. Successful characterization methods for complex soil systems are based on (1) an adequate parameterization of the subsurface, capable of capturing both random and structured aspects of the heterogeneous sy...

We propose Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork, h, is a neural network which learns to transform a simple noise distribution, p( ) = N (0, I), to a distribution q(θ) . = q(h( )) over the parameters θ of another neural network (the "primary network"). We train q with variational inference, using an invertible h to ena...

The study of malaria spatial epidemiology has benefited from recent advances in geographic information system and geostatistical modelling. Significant progress in earth observation technologies has led to the development of moderate, high and very high resolution imagery. Extensive literature exists on the relationship between malaria and environmental/climatic factors in different geographica...