surp.fit: Evaluate the fit of surprisal curves to binned psychometric...

In fda: Functional Data Analysis

Evaluate the fit of surprisal curves to binned psychometric data.

Description

Evaluate the error sum of squares, its gradient and its hessian for the fit of surprisal curves to binned psychometric data. The function value is optimized by function smooth.surp in package TestGardener.

Usage

surp.fit(x, surpList)

Arguments

x	The parameter vector, which is the vectorized form of the K by M-1 coefficient matrix for the functional data object.
surpList	A named list object containing objects essential to evaluating the fitting criterion. See smooth.surp.R for the composition of this list.

Value

A named list object for the returned objects with these names:

PENSSE:	The error sum of squares associated with parameter value x.
DPENSSE:	A column vector containing gradient of the error sum of squares.
D2PENSSE:	A square matrix of hessian values.

Author(s)

Juan Li and James Ramsay

References

Ramsay, J. O., Li J. and Wiberg, M. (2020) Full information optimal scoring. Journal of Educational and Behavioral Statistics, 45, 297-315.

Ramsay, J. O., Li J. and Wiberg, M. (2020) Better rating scale scores with information-based psychometrics. Psych, 2, 347-360.

http://testgardener.azurewebsites.net

See Also

smooth.surp

fda documentation built on May 31, 2023, 9:19 p.m.