A test-theoretic approach to observed-score equating

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Observed-score equating using the marginal distributions of two tests is not necessarily the universally best approach it has been claimed to be. On the other hand, equating using the conditional distributions given the ability level of the examinee is theoretically ideal. Possible ways of dealing with the requirement of known ability are discussed, including such methods as conditional observed-score equating at point estimates or posterior expected conditional equating. The methods are generalized to the problem of observed-score equating with a multivariate ability structure underlying the scores.
Original languageEnglish
Pages (from-to)437-456
Number of pages19
JournalPsychometrika
Volume65
Issue number4
DOIs
Publication statusPublished - 2000

Fingerprint

Point Estimate
Marginal Distribution
Conditional Distribution
Requirements

Keywords

  • IR-60231
  • METIS-135574
  • Observed-score equating - equipercentile method - equating criteria - multidimensionality

Cite this

@article{5238bf1caeac4483a4a4ada4f7d345e0,
title = "A test-theoretic approach to observed-score equating",
abstract = "Observed-score equating using the marginal distributions of two tests is not necessarily the universally best approach it has been claimed to be. On the other hand, equating using the conditional distributions given the ability level of the examinee is theoretically ideal. Possible ways of dealing with the requirement of known ability are discussed, including such methods as conditional observed-score equating at point estimates or posterior expected conditional equating. The methods are generalized to the problem of observed-score equating with a multivariate ability structure underlying the scores.",
keywords = "IR-60231, METIS-135574, Observed-score equating - equipercentile method - equating criteria - multidimensionality",
author = "{van der Linden}, {Willem J.}",
year = "2000",
doi = "10.1007/BF02296337",
language = "English",
volume = "65",
pages = "437--456",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer",
number = "4",

}

A test-theoretic approach to observed-score equating. / van der Linden, Willem J.

In: Psychometrika, Vol. 65, No. 4, 2000, p. 437-456.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A test-theoretic approach to observed-score equating

AU - van der Linden, Willem J.

PY - 2000

Y1 - 2000

N2 - Observed-score equating using the marginal distributions of two tests is not necessarily the universally best approach it has been claimed to be. On the other hand, equating using the conditional distributions given the ability level of the examinee is theoretically ideal. Possible ways of dealing with the requirement of known ability are discussed, including such methods as conditional observed-score equating at point estimates or posterior expected conditional equating. The methods are generalized to the problem of observed-score equating with a multivariate ability structure underlying the scores.

AB - Observed-score equating using the marginal distributions of two tests is not necessarily the universally best approach it has been claimed to be. On the other hand, equating using the conditional distributions given the ability level of the examinee is theoretically ideal. Possible ways of dealing with the requirement of known ability are discussed, including such methods as conditional observed-score equating at point estimates or posterior expected conditional equating. The methods are generalized to the problem of observed-score equating with a multivariate ability structure underlying the scores.

KW - IR-60231

KW - METIS-135574

KW - Observed-score equating - equipercentile method - equating criteria - multidimensionality

U2 - 10.1007/BF02296337

DO - 10.1007/BF02296337

M3 - Article

VL - 65

SP - 437

EP - 456

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 4

ER -