Calibrating essay markers with the partial credit model

Geoff N Masters; Siek Toon Khoo

Calibrating essay markers with the partial credit model

Research output: Contribution to conference › Presentation

Abstract

This paper shows how a range of differences in marker behaviour, including leniency/severity and central tendency, can be detected and investigated using the Rasch partial credit model. The method allows for variations in the use of rating categories by estimating a set of rating 'thresholds' for each assessor. By calibrating each assessor's rating behaviour in this way, the method automatically takes account of detected differences among assessors in the measurement process.

Original language	English
Publication status	Published - Apr 1994
Externally published	Yes
Event	Annual Meeting of the American Educational Research Association - Duration: 1 Apr 1994 → …

Conference

Conference	Annual Meeting of the American Educational Research Association
Period	1/04/94 → …

Disciplines

Educational Assessment, Evaluation, and Research

Cite this

@conference{63dd0014e4864591aef6c717d501703f,

title = "Calibrating essay markers with the partial credit model",

abstract = " This paper shows how a range of differences in marker behaviour, including leniency/severity and central tendency, can be detected and investigated using the Rasch partial credit model. The method allows for variations in the use of rating categories by estimating a set of rating 'thresholds' for each assessor. By calibrating each assessor's rating behaviour in this way, the method automatically takes account of detected differences among assessors in the measurement process.",

author = "Masters, \{Geoff N\} and Khoo, \{Siek Toon\}",

year = "1994",

month = apr,

language = "English",

note = "Annual Meeting of the American Educational Research Association ; Conference date: 01-04-1994",

}

TY - CONF

T1 - Calibrating essay markers with the partial credit model

AU - Masters, Geoff N

AU - Khoo, Siek Toon

PY - 1994/4

Y1 - 1994/4

N2 - This paper shows how a range of differences in marker behaviour, including leniency/severity and central tendency, can be detected and investigated using the Rasch partial credit model. The method allows for variations in the use of rating categories by estimating a set of rating 'thresholds' for each assessor. By calibrating each assessor's rating behaviour in this way, the method automatically takes account of detected differences among assessors in the measurement process.

AB - This paper shows how a range of differences in marker behaviour, including leniency/severity and central tendency, can be detected and investigated using the Rasch partial credit model. The method allows for variations in the use of rating categories by estimating a set of rating 'thresholds' for each assessor. By calibrating each assessor's rating behaviour in this way, the method automatically takes account of detected differences among assessors in the measurement process.

M3 - Presentation

T2 - Annual Meeting of the American Educational Research Association

Y2 - 1 April 1994

ER -