Premium
ITEM DIFFICULTY LEVEL AND SEQUENCE EFFECTS IN MULTIPLE‐CHOICE ACHIEVEMENT TESTS
Author(s) -
HUCK SCHUYLER W.,
BOWERS NORMAN D.
Publication year - 1972
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.1745-3984.1972.tb00765.x
Subject(s) - sequence (biology) , psychology , achievement test , generalization , test (biology) , variance (accounting) , item response theory , statistics , item analysis , econometrics , mathematics education , standardized test , psychometrics , mathematics , developmental psychology , mathematical analysis , paleontology , genetics , accounting , business , biology
Certain testing authorities have implied that the proportion of examinees who answer an item correctly may be influenced by the difficulty of the immediately preceding item. If present, such a “sequence effect” would cause p (as an estimate of item difficulty level) to misrepresent an item's “true” level of difficulty. To investigate this hypothesis, a balanced Latin square design was used to rearrange examination items into various test forms. A unique analysis of variance procedure was used to analyze the resulting data. The alleged sequence effect was not found. Certain limitations preclude the generalization of this finding to all students or to all testing situations. However, the evidence provided by this investigation does suggest that comments relating to sequence effects should be qualified as compared with presently appearing statements.