bbgdm.fit: bbgdm.fit objects
In skiptoniam/bbgdm: Bayesian Bootstrap Generalised Dissimilarity Models.

Description Usage Arguments Value Author(s)

function for fitting a bbgdm model. This is essential a single gdm and builds the core of bbgdm. Like glm.fit a number of options can be defined. Like: optimisation method optim or nlminb, link function make.link.

bbgdm.fit(X, y, wt = NULL, link, optim.meth = "optim", est.var = TRUE,
  trace = FALSE, prior = FALSE, control = bbgdm.control())

bbgdm.control(method = "BFGS", maxit = 1000, hessian = FALSE,
  trace = FALSE, start = NULL, fsmaxit = 20, fstol = 1e-05, cores = 1,
  ...)

negexp()

`X`	Model matirx of predictors, see `model.matrix`.
`y`	Model response, see `model.response`.
`wt`	weights for model.
`link`	character link functions. default is 'logit', can call other link functions `make.link` or a 'negexp' custom link function (e.g., Ferrier etal., 2007).
`optim.meth`	optimisation method options avaliable are 'optim' and 'nlmnib', calls either method `optim` or `nlminb`.
`est.var`	logical if true estimated parameter variance using optimiser.
`trace`	options looks at `optim` for details.
`prior`	numeric vector of starting values for intercept and splines.
`control`	control option from optim see `bbgdm.control` or `optim`.
`method`	characters string specifying the method argument passed to optim.
`maxit`	integer specifying the maxit argument (maximal number of iterations) passed to optim.
`hessian`	logical. Should the numerical Hessian matrix from the optim output be used for estimation of the covariance matrix? By default the analytical solution is employed. For details see below.
`start`	an optional vector with starting values for all parameters.
`fsmaxit`	integer specifying maximal number of additional (quasi) Fisher scoring iterations. For details see below.
`fstol`	numeric tolerance for convergence in (quasi) Fisher scoring. For details see `optim`.
`cores`	the number of cores to use in fitting.
`...`	for `bbgdm.fit()` or more `bbgdm.control()`.