Parallelism Constraint Matrices

Returns a logical vector from a test of whether an object such as a matrix or VGLM object corresponds to a parallelism assumption.

Usage

is.parallel.matrix(object, ...)
is.parallel.vglm(object, type = c("term", "lm"), ...)

Arguments

object

an object such as a constraint matrix or a vglm object.

type

passed into constraints.

...

additional optional arguments. Currently unused.

Details

These functions may be useful for categorical models such as propodds, cumulative, acat, cratio, sratio, multinomial.

Value

A vector of logicals, testing whether each constraint matrix is a one-column matrix of ones. Note that parallelism can still be thought of as holding if the constraint matrix has a non-zero but constant values, however, this is currently not implemented. No checking is done that the constraint matrices have the same number of rows.

See also

constraints, vglm.

Examples

if (FALSE)  require("VGAMdata")
fit <- vglm(educ ~ sm.bs(age) * sex + ethnicity,
            cumulative(parallel = TRUE), head(xs.nz, 200))
#> Error in eval(mf, parent.frame()): object 'xs.nz' not found
is.parallel(fit)
#> Error in h(simpleError(msg, call)): error in evaluating the argument 'object' in selecting a method for function 'is.parallel': object 'fit' not found
is.parallel(fit, type = "lm")  # For each column of the LM matrix
#> Error in h(simpleError(msg, call)): error in evaluating the argument 'object' in selecting a method for function 'is.parallel': object 'fit' not found
 # \dontrun{}