NotesFAQContact Us
Search Tips
ERIC Number: ED262084
Record Type: Non-Journal
Publication Date: 1985
Pages: 17
Abstractor: N/A
Reference Count: N/A
Statistical Equating of Direct Writing Assessment.
Phillips, Gary W.
This paper provides empirical data on two approaches to statistically equate scores derived from the direct assessment of writing. These methods are linear equating and equating based on the general polychotomous form of the Rasch model. Data from the Maryland Functional Writing Test are used to equate scores obtained from two prompts given in 1984 to the scores obtained from two different prompts administered in 1983. Two 1983 writing prompts were administered to 351 examinees, while two 1984 prompts were administered to 347 examinees. The results suggest two conclusions: (1) the effects of statistical equating depends in part on where within the score range the passing score happens to be; and (2) different results are obtained with different equating methodologies. It is recommended that the equating of direct writing assessments be accomplished with the general polychotomous form of the Rasch model. All the advantages of the Rasch model for multiple choice tests, potentially, may be realized in direct writing assessment. (PN)
Publication Type: Speeches/Meeting Papers; Reports - Research
Education Level: N/A
Audience: Researchers
Language: English
Sponsor: N/A
Authoring Institution: N/A