gavinsimpson
commented
9 hours ago Hi @nicholasjclark; would you mind prepping a PR to add something like your example paragraph? It doesn't need to be as detailed as what you have above, perhaps:
mvgam fits Bayesian State-Space Generalized Additive Models for many data types including counts, binary observations, proportions, non-negative real values and unbounded real values. mvgam can fit a wide range of hierarchical ecological models including N-mixture models, Latent Variable-based Joint Species Distribution Models, and multivariate time series models with imperfect detection.
?
The
{mvgam}package can now fit flexible latent variable models (including JSDMs) using the newjsdgam()function. Would it be possible to add this to the Model-based multivariate analysis section section using something like the following:mvgam fits Bayesian State-Space Generalized Additive Models for many data types including counts, binary observations, proportions, non-negative real values and unbounded real values. By leveraging functionalities from brms, mgcv and splines2 packages, mvgam models can include diverse predictor effects including penalized splines, Gaussian Processes, random interecepts / slopes and monotonic functions. Combined with support for a variety of temporal and spatial autocorrelation structures, this flexibility allows mvgam to fit a wide range of hierarchical ecological models including N-mixture models, Latent Variable-based Joint Species Distribution Models, and multivariate time series models with imperfect detection. The package uses Stan for efficient Hamiltonian Monte Carlo inference.