STooDs is a framework to build and estimate probabilistic models for data varying in Space, Time or other Dimensions. A typical STooDs case study can be described as follows:
- The target dataset contains the values taken by one of several predictand variables varying along one or more dimensions.
- Each variable in the dataset is assumed to follow a distribution whose parameters may vary along the same dimensions as the dataset.
- This variability is specified by regression formulas that may use parameters, covariates and processes.
The current release is a computational engine and mostly aims at generating MCMC samples from the posterior distribution associated with the model and the data.