A sparse grid used for numerical integration to get the likelihood.
Hessian
A logical, if TRUE, the hessian is computed and returned.
tol
numerical tolerance.
...
Additional argument.
Details
A Gaussian copula with a correlation structure obtained from a random
intercept or random intercept / random slope model (that is, clustered or
longitudinal data can by modelled only) is used to capture the
correlations whereas the marginal distributions are described by a
transformation model. The methodology is described in Barbanti and Hothorn
(2022) and examples are given in the mtram package vignette.
This is a proof-of-concept implementation. Only coef() and
logLik() methods are available at the moment.
References
Luisa Barbanti and Torsten Hothorn (2023). A Transformation Perspective on
Marginal and Conditional Models, Biostatistics, tools:::Rd_expr_doi("10.48550/arXiv.1910.09219").