NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED017810
Record Type: RIE
Publication Date: 1967-Oct-28
Pages: 22
Abstractor: N/A
Reference Count: 0
ISBN: N/A
ISSN: N/A
SAMPLE-FREE TEST CALIBRATION AND PERSON MEASUREMENT. PAPER PRESENTED AT THE NATIONAL SEMINAR ON ADULT EDUCATION RESEARCH (CHICAGO, FEBRUARY 11-13, 1968).
WRIGHT, BENJAMIN D.
OBJECTIVITY IN MENTAL TESTING REQUIRES THAT TEST CALIBRATION BE INDEPENDENT OF WHICH PERSONS ARE USED FOR THE CALIBRATION AND THAT PERSON MEASUREMENT BE INDEPENDENT OF WHICH ITEMS ARE USED FOR THE MEASUREMENT. PRESENT PRACTICE IS NOT OBJECTIVE, BUT COULD BE SO, AS SHOWN BY THE EXAMPLE HERE PRESENTED. DATA COME FROM THE RESPONSES OF 976 LAW STUDENTS TO 48 READING COMPREHENSION ITEMS ON THE LAW SCHOOL ADMISSIONS TEST. THE POSSIBILITY OF PERSON FREE TEST CALIBRATION IS DEMONSTRATED BY SHOWING THAT A CALIBRATION BASED ON THE RESPONSES OF A DUMB GROUP OF STUDENTS CAN BE NEARLY IDENTICAL WITH ONE BASED ON A SMART GROUP. THE POSSIBILITY OF ITEM FREE PERSON MEASUREMENT IS DEMONSTRATED BY SHOWING THAT ABILITY ESTIMATES MADE FROM SCORES ON AN EASY TEST CAN BE STATISTICALLY EQUIVALENT TO THOSE MADE FROM A HARD TEST. THE MEASUREMENT MODEL WHICH MAKES THIS OBJECTIVITY POSSIBLE WAS DEVELOPED BY GEORG RASCH. IN THIS MODEL THE ODDS OF SUCCESS ON A TEST ITEM ARE HYPOTHESIZED TO BE GIVEN BY THE PRODUCT OF THE PERSON'S ABILITY AND THE ITEM'S EASINESS. IN ORDER TO FIT THIS MODEL ITEMS MUST BE CHOSEN OR CONSTRUCTED TO HAVE SIMILAR DISCRIMINATION. THE RESULTING MEASURES OF PERSON ABILITY AND ITEM EASINESS ARE ON A RATIO SCALE WITH A NATURAL ZERO AND A DEFINABLE UNIT. THIS PAPER WAS PRESENTED AT THE NATIONAL SEMINAR ON ADULT EDUCATION RESEARCH, CHICAGO, FEBRUARY 11-13, 1968. (AUTHOR/RT)
Publication Type: N/A
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A
Identifiers: Rasch Model