FIM_logistic: Fisher Information Matrix for the 2-Parameter Logistic (2PL)...

In ICAOD: Optimal Designs for Nonlinear Statistical Models by Imperialist Competitive Algorithm (ICA)

Description

It provides the cpp function for FIM for the model ~1/(1 + exp(-b *(x - a))). In item response theory (IRT), a is the item difficulty parameter, b is the item discrimination parameter and x is the person ability parameter.

Usage

FIM_logistic(x, w, param)

Arguments

x	Vector of design points.
w	Vector of design weight. Its length must be equal to the length of x and sum(w) = 1.
param	Vector of values for the model parameters c(a, b).

Details

It can be shown that minimax and standardized D-optimal designs for the 2PL model is symmetric around point aM = (aL + aU)/2 where aL and aU are the lower bound and upper bound for parameter a, respectively. In ICA.control, arguments sym and sym_point can be used to specify aM and find accurate symmetric optimal designs.

Value

Fisher information matrix.

Examples

FIM_logistic(x = c(1, 2), w = c(.5, .5), param = c(2, 1))

Example output

           [,1]       [,2]
[1,] 0.22330597 0.09830597
[2,] 0.09830597 0.09830597

ICAOD documentation built on Oct. 23, 2020, 6:40 p.m.