Item Quality and Appropriateness of Response Processes

Turner, Castellano B.; Fiske, Donald W.

doi:10.1177/001316446802800208

Cited by 24 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…What is probably needed is more information about the transaction between each subject and each item. Appropriate response processes may occur more frequently for some items (Turner and Fiske, 1968) and perhaps for some subjects.…”

Section: Resultsmentioning

confidence: 99%

Homogeneity of Sample and of Test Responses

Fiske

1973

Educational and Psychological Measurement

Self Cite

View full text Add to dashboard Cite

EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT 1973, 33, 239-253. THE observed homogeneity of a test can be interpreted from two approaches. In terms of the test stimuli, homogeneity is the extent to which the several items elicit responses relevant to the same psychological disposition. In terms of the subject sample, the perceptions and meanings assigned by the several subjects to each of the items must be highly similar if a test is to show high homogeneity. It also seems reasonable to assume that similarity in reaction to the testing situation and to being tested should contribute to homogeneity of test responses, such similarity being greater for subgroups of subjects classified on the basis of some separate intrinsic characteristic than for the same subjects lumped together into one total group. It seems obvious that if the test task and the stimuli are interpreted in diverse ways by different subjects, the homogeneity of the responses will be minimal.This orientation leads to the proposition that the more homogeneous the subjects in an experimental sample, the more homogeneous should be their test responses. In this hypothesis, the two uses of the term homogeneous have somewhat different referents. Homogeneity of test responses refers to psychometric indices, including the standard coefficient of internal consistency, detailed by

show abstract

Section: Resultsmentioning

confidence: 99%

Homogeneity of Sample and of Test Responses

Fiske

1973

Educational and Psychological Measurement

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although interpretive ambiguity was signifi cantly related to response ambiguity, items high on interpretive ambiguity but low on response ambiguity were found to be keyed more frequently on 157 different MMPI scales (12) . Items also differ in the extent to which they elicit in subj ects the response processes intended by the test construc tor, these differences being related to item-test homogeneity (219). The for mal interchange of persons and items in analyzing a data matrix brings out their quite different psychological roles and throws a little light on the per son-item interaction (72) .…”

Section: New Methodological Contributionsmentioning

confidence: 99%

Theory and Techniques of Personality Measurement

Fiske¹,

Pearson²

1970

Annu. Rev. Psychol.

Self Cite

View full text Add to dashboard Cite

This chapter is one of the intermittent series which has had "assess ment" in its title. The authors have dropped that term because of its impre cision and its connotations. Assessment has often been used to refer to the combining of measures, usually by human judgment, to predict a criterion. But personality measurement as a whole involves the combination or reduc tion of observations to obtain an index and is concerned with much more than the prediction of criteria. Additionally, the terms assessment and crite ria have an evaluative flavor; while adequacy of functioning is involved in much of personality, a science of personality must not be limited to norma tive considerations. Finally, assessment has the connotation of dealing with the whole person. It seems quite clear that we cannot have a science of the whole person, or even of substantial segments of personality, until we un derstand the components.Most concepts in the personality field are so broad and heterogeneous in their referents that when one concept is used to describe different persons, it is very doubtful that the identical attribute is applied to each. The task fac ing personality today is the identifi cation and delineation of attributes which can be uniformly applied to persons, the objects of this science, with the specifi c applications of each attribute differing only in quantity, not quality. Coordinate with that task is the work of developing operations for measur ing each of these attributes. Such procedures must be standardized so that the measurements can, in principle, be replicated for the same persons and, particularly critical in this area, so that the measurements are getting at the same attribute in the different persons measured, without any sizable per son-instrument interaction. This chapter is concerned with the extent to which these standards are being approximated in personality measurement today.A science develops by an interactive or cyclical process, observations leading to concepts, and concepts guiding the next set of observations. In personality, an infi nity of observations has been conceptualized in a variety of sets of terms with general statements about them. These literary or even

show abstract

“…Those who frequently say yes may err through claiming to possess too many traits that are statistically infrequent, and those who frequently say no may err in the opposite direction by denying that they possess traits that are actually quite common. Researches like those of Turner and Fiske (1968) leave little doubt that inferential processes of markedly varying appropriateness play a major role in responding to items in personality inventories.…”

Section: Factor Analysis Of the Datamentioning

confidence: 99%

A latent-structure model for answering personal questions.

Damarin¹

1970

Psychological Bulletin

View full text Add to dashboard Cite

A latent-structure model for answering true-false questionnaire items is shown to predict a circular ordering among some MMPI scales that were used in a recent study by Wiggins and Lovell (1965). A circular ordering can be demonstrated, but certain systematic departures from the predicted effects also occur. The data suggest the operation of three latent traits: self-descriptive accuracy, favorable bias, and a tendency to endorse items that are neutral in the sense of being unrelated to the other two traits. Alternative interpretations of the results are discussed together with suggestions for further research.

show abstract

Item Quality and Appropriateness of Response Processes

Cited by 24 publications

References 8 publications

Homogeneity of Sample and of Test Responses

Homogeneity of Sample and of Test Responses

Theory and Techniques of Personality Measurement

A latent-structure model for answering personal questions.

Contact Info

Product

Resources

About