Scalable Gaussian-Process Approximations
Vecchia Laplace extension of GPVecchia for non-Gaussian data
create the sparse triangular L matrix for specific parameters
create the sparse triangular U matrix for specific parameters
extract the required elements from the covariance matrix
Calculate the covariance values required by HV for matrix factors pass...
GPvecchia: fast, scalable Gaussian process approximations
Incomplete Cholesky decomposition of a sparse matrix passed in the com...
Wrapper for incomplete Cholesky decomposition
Calculate Matern covariance function
Sorted coordinate ordering
Distance to specified point ordering
Maximum minimum distance ordering for prediction
Maximum minimum distance ordering
Middle-out ordering
Outside-in ordering
selected inverse of a sparse matrix
compute covariance matrix from V.ord Do not run this function for larg...
estimate mean and covariance parameters of a Matern covariance functio...
Wrapper for VL version of vecchia_likelihood
Wrapper for VL version of vecchia_likelihood
Wrapper for VL version of vecchia_prediction
evaluation of the likelihood
linear combination of predictions compute the distribution of a linear...
make spatial predictions using Vecchia based on estimated parameters
Vecchia prediction
specify a general vecchia approximation
Fast scalable Gaussian process approximations, particularly well suited to spatial (aerial, remote-sensed) and environmental data, described in more detail in Katzfuss and Guinness (2017) <doi:10.48550/arXiv.1708.06302>. Package also contains a fast implementation of the incomplete Cholesky decomposition (IC0), based on Schaefer et al. (2019) <doi:10.48550/arXiv.1706.02205> and MaxMin ordering proposed in Guinness (2018) <doi:10.48550/arXiv.1609.05372>.