Cross-validating item parameter estimation in adaptive testing

Willem J. van der Linden; Cornelis A.W. Glas

Cross-validating item parameter estimation in adaptive testing

Willem J. van der Linden, Cornelis A.W. Glas

Faculty of Behavioural, Management and Social Sciences

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

Abstract

From a statistical point of view, adaptive testing belongs to the class of problems of selecting a best subset of random variables. As in any other instance of this problem, adaptive testing is likely to capitalize on estimation error. An empirical example of the phenomenon is discussed, and a strategy for cross-validating results from adaptive testing is proposed. Results from a simulation study on the strategy are presented.

Original language	Undefined
Title of host publication	Essays on item response theory
Editors	Anne Boomsma, Marijtje A.J. van Duijn, Tom A.B. Snijders
Publisher	Springer
Pages	205-219
ISBN (Print)	9780387951478
Publication status	Published - 2001

Publication series

Name	Lecture notes in statistics
Publisher	Springer
Number	157
Volume	0930-0325

Keywords

IR-104258

Access to Document

http://doi.org/10.1007/978-1-4613-0169-1_12

Cite this

@inbook{4684d1831d754b479e1d6598cbd235a2,

title = "Cross-validating item parameter estimation in adaptive testing",

abstract = "From a statistical point of view, adaptive testing belongs to the class of problems of selecting a best subset of random variables. As in any other instance of this problem, adaptive testing is likely to capitalize on estimation error. An empirical example of the phenomenon is discussed, and a strategy for cross-validating results from adaptive testing is proposed. Results from a simulation study on the strategy are presented.",

keywords = "IR-104258",

author = "{van der Linden}, {Willem J.} and Glas, {Cornelis A.W.}",

year = "2001",

language = "Undefined",

isbn = "9780387951478",

series = "Lecture notes in statistics",

publisher = "Springer",

number = "157",

pages = "205--219",

editor = "Anne Boomsma and {van Duijn}, {Marijtje A.J.} and Snijders, {Tom A.B.}",

booktitle = "Essays on item response theory",

address = "Netherlands",

}

Cross-validating item parameter estimation in adaptive testing. / van der Linden, Willem J.; Glas, Cornelis A.W.

Essays on item response theory. ed. / Anne Boomsma; Marijtje A.J. van Duijn; Tom A.B. Snijders. Springer, 2001. p. 205-219 (Lecture notes in statistics; Vol. 0930-0325, No. 157).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic

TY - CHAP

T1 - Cross-validating item parameter estimation in adaptive testing

AU - van der Linden, Willem J.

AU - Glas, Cornelis A.W.

PY - 2001

Y1 - 2001

N2 - From a statistical point of view, adaptive testing belongs to the class of problems of selecting a best subset of random variables. As in any other instance of this problem, adaptive testing is likely to capitalize on estimation error. An empirical example of the phenomenon is discussed, and a strategy for cross-validating results from adaptive testing is proposed. Results from a simulation study on the strategy are presented.

AB - From a statistical point of view, adaptive testing belongs to the class of problems of selecting a best subset of random variables. As in any other instance of this problem, adaptive testing is likely to capitalize on estimation error. An empirical example of the phenomenon is discussed, and a strategy for cross-validating results from adaptive testing is proposed. Results from a simulation study on the strategy are presented.

KW - IR-104258

M3 - Chapter

SN - 9780387951478

T3 - Lecture notes in statistics

SP - 205

EP - 219

BT - Essays on item response theory

A2 - Boomsma, Anne

A2 - van Duijn, Marijtje A.J.

A2 - Snijders, Tom A.B.

PB - Springer

ER -