mf7: The full Fisher Information Matrix (FIM) for one individual...

In andrewhooker/PopED: Population (and Individual) Optimal Experimental Design

The full Fisher Information Matrix (FIM) for one individual Calculating one model switch at a time, good for large matrices.

Description

Compute the full FIM for one individual given specific model(s), parameters, design and methods. This computation calculates the FIM for each model switch separately. Correlations between the models parameters are assumed to be zero.

Usage

mf7(model_switch, xt_ind, x, a, bpop, d, sigma, docc, poped.db)

Arguments

model_switch	A vector that is the same size as xt, specifying which model each sample belongs to.
x	A vector for the discrete design variables.
a	A vector of covariates.
bpop	The fixed effects parameter values. Supplied as a vector.
d	A between subject variability matrix (OMEGA in NONMEM).
sigma	A residual unexplained variability matrix (SIGMA in NONMEM).
docc	A between occasion variability matrix.
poped.db	A PopED database.

Value

As a list:

ret	The FIM for one individual
poped.db	A PopED database

See Also

Other FIM: LinMatrixH(), LinMatrixLH(), LinMatrixL_occ(), calc_ofv_and_fim(), ed_laplace_ofv(), ed_mftot(), efficiency(), evaluate.e.ofv.fim(), evaluate.fim(), gradf_eps(), mf3(), mftot(), ofv_criterion(), ofv_fim()

andrewhooker/PopED documentation built on Nov. 23, 2023, 1:37 a.m.