Dopt

class pyoptex.doe.fixed_structure.splitk_plot.metric.Dopt(cov=None)

The D-optimality criterion. Computes the geometric mean in case multiple Vinv are provided.

Attributes

covfunc(Y, X)

A function computing the covariate parameters and potential extra random effects.

Minvnp.array(3d)

The inverses of the information matrices.

Pnp.array(2d)

The P-matrix in the update formula.

Unp.array(2d)

The U-matrix in the update formula.

Dnp.array(2d)

The D-matrix in the update formula.

__init__(cov=None)

Creates the metric

Parameters

covfunc(Y, X)

The covariance function

Methods

Dopt.accepted(Y, X, params, update)	Updates the internal state when the updated design was accepted (and therefore better).
Dopt.call(Y, X, params)	Computes the D-optimality criterion.
Dopt.init(Y, X, params)	Initializes the metric for each random initialization of the coordinate-exchange algorithm.
Dopt.preinit(params)	Pre-initializes the metric
Dopt.update(Y, X, params, update)	Computes the update to the metric according to update.