Premium
Clarification to “Examining Rater Errors in the Assessment of Written Composition With a Many‐Faceted Rasch Model”
Author(s) -
Engelhard George
Publication year - 1996
Publication title -
journal of educational measurement
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.917
H-Index - 47
eISSN - 1745-3984
pISSN - 0022-0655
DOI - 10.1111/j.1745-3984.1996.tb00483.x
Subject(s) - rasch model , bar chart , histogram , computer science , scaling , polytomous rasch model , chart , item response theory , pie chart , row , statistics , artificial intelligence , natural language processing , data mining , psychometrics , mathematics , database , image (mathematics) , geometry
In the article “Examining Rater Errors in the Assessment of Written Composition With a Many‐Faceted Rasch Model” (JEM, Volume 31, Number 2, Summer 1994), the data presented in Figure 3 may be misleading. The “four clear spikes” (p. 106) that appear in Figure 3 were highlighted by the automatic scaling procedure used by the computer program that generated this histogram; as is well known, the use of different scaling units would yield histograms with different shapes (Moore & McCabe, 1993). For example, when the same data are presented as a bar chart (see Figure 1 below) rather than as a histogram, the four spikes are not evident. As graphical procedures become more readily available to measurement researchers, additional research and discussion are needed regarding standards for evaluating data displays that do not simply reproduce the actual data values.