Approximating the conditional distribution of person fit indexes for checking the rasch model

Edward J. Bedrick

doi:10.1007/BF02295274

Approximating the conditional distribution of person fit indexes for checking the rasch model

Edward J. Bedrick

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

We present a simple approximation to the conditional distribution of goodness-of-fit statistics for the Rasch model, assuming that the item difficulties are known. The approximation is easily programmed, and gives relatively accurate assessments of conditional p-values for tests of length 10 or more. A few generalizations are discussed.

Original language	English (US)
Pages (from-to)	191-199
Number of pages	9
Journal	Psychometrika
Volume	62
Issue number	2
DOIs	https://doi.org/10.1007/BF02295274
State	Published - Jun 1997
Externally published	Yes

Keywords

Edgeworth expansion
Exact p-value
Saddlepoint approximation

ASJC Scopus subject areas

General Psychology
Applied Mathematics

Access to Document

10.1007/BF02295274

Cite this

@article{f6b80d3c77834adaae3e782af85e3ebb,

title = "Approximating the conditional distribution of person fit indexes for checking the rasch model",

abstract = "We present a simple approximation to the conditional distribution of goodness-of-fit statistics for the Rasch model, assuming that the item difficulties are known. The approximation is easily programmed, and gives relatively accurate assessments of conditional p-values for tests of length 10 or more. A few generalizations are discussed.",

keywords = "Edgeworth expansion, Exact p-value, Saddlepoint approximation",

author = "Bedrick, {Edward J.}",

year = "1997",

month = jun,

doi = "10.1007/BF02295274",

language = "English (US)",

volume = "62",

pages = "191--199",

journal = "Psychometrika",

issn = "0033-3123",

publisher = "Cambridge University Press",

number = "2",

}

TY - JOUR

T1 - Approximating the conditional distribution of person fit indexes for checking the rasch model

AU - Bedrick, Edward J.

PY - 1997/6

Y1 - 1997/6

N2 - We present a simple approximation to the conditional distribution of goodness-of-fit statistics for the Rasch model, assuming that the item difficulties are known. The approximation is easily programmed, and gives relatively accurate assessments of conditional p-values for tests of length 10 or more. A few generalizations are discussed.

AB - We present a simple approximation to the conditional distribution of goodness-of-fit statistics for the Rasch model, assuming that the item difficulties are known. The approximation is easily programmed, and gives relatively accurate assessments of conditional p-values for tests of length 10 or more. A few generalizations are discussed.

KW - Edgeworth expansion

KW - Exact p-value

KW - Saddlepoint approximation

UR - http://www.scopus.com/inward/record.url?scp=0040304556&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0040304556&partnerID=8YFLogxK

U2 - 10.1007/BF02295274

DO - 10.1007/BF02295274

M3 - Article

AN - SCOPUS:0040304556

SN - 0033-3123

VL - 62

SP - 191

EP - 199

JO - Psychometrika

JF - Psychometrika

IS - 2

ER -

Approximating the conditional distribution of person fit indexes for checking the rasch model

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this