Weather modelling using a multivariate latent Gaussian model

Rainfall Modelling Using a Latent Gaussian Variable

A monotonic transformation is applied to hourly rainfall data to achieve marginal normality. This deenes a latent Gaussian variable, with zero rainfall corresponding to censored values below a threshold. Autocor-relations of the latent v ariable are estimated by maximum likelihood. The goodness of t of the model to Edinburgh rainfall data is comparable with that of existing point process models...

Graphical Gaussian modelling of multivariate time series with latent variables

In time series analysis, inference about causeeffect relationships among multiple times series is commonly based on the concept of Granger causality, which exploits temporal structure to achieve causal ordering of dependent variables. One major problem in the application of Granger causality for the identification of causal relationships is the possible presence of latent variables that affect ...

A latent Gaussian model for multivariate consumption data

We propose a multivariate statistical model for individual consumption of multiple food types, to provide a more objective basis for exposure assessment from chronic consumption. Intake of each type of food is modelled by a latent Gaussian variable, where intake is zero if the latent variable is below a threshold, and otherwise is a monotonically increasing function of the latent variable. Furt...

Multivariate latent Gaussian random field mixture models

A latent variable model for multivariate discretization

We describe a new method for multivariate discretization based on the use of a latent variable model. The method is proposed as a tool to extend the scope of applicability of machine learning algorithms that handle discrete variables only.