Detection of Item Bias Using Analyses of Response Patterns

Item Bias Analysis of the Young Schema-Questionnaire for Psychopathology, Gender, and Educational Level

European Journal of Psychological Assessment ◽

10.1027/1015-5759/a000044 ◽

2011 ◽

Vol 27 (1) ◽

pp. 65-70 ◽

Cited By ~ 11

Author(s):

Marleen M. Rijkeboer ◽

Huub van den Bergh ◽

Jan van den Bout

Keyword(s):

Educational Level ◽

Cross Validation ◽

Item Bias ◽

Response Patterns ◽

Dutch Population ◽

Bias Analysis ◽

Young Schema Questionnaire ◽

Item Functioning ◽

Item Level ◽

Schema Questionnaire

This study examines the construct validity of the Young Schema-Questionnaire at the item level in a Dutch population. Possible bias of items in relation to the presence or absence of psychopathology, gender, and educational level was analyzed, using a cross-validation design. None of the items of the YSQ exhibited differential item functioning (DIF) for gender, and only one item showed DIF for educational level. Furthermore, item bias analysis did not identify DIF for the presence or absence of psychopathology in as much as 195 of the 205 items comprising the YSQ. Ten items, however, spread over the questionnaire, were found to yield relatively inconsistent response patterns for patients and nonclinical participants.

Download Full-text

Stimulus Ratio Effects on Speech Discrimination by Children and Adults

Journal of Speech Language and Hearing Research ◽

10.1044/jshr.3403.671 ◽

1991 ◽

Vol 34 (3) ◽

pp. 671-678 ◽

Cited By ~ 9

Author(s):

Joan E. Sussman

Keyword(s):

Discrimination Task ◽

Response Pattern ◽

Response Patterns ◽

Speech Discrimination ◽

Adult Group ◽

Discrimination Accuracy ◽

Formant Frequency ◽

Response Strategies ◽

Place Of Articulation ◽

Adults And Children

This investigation examined the response strategies and discrimination accuracy of adults and children aged 5–10 as the ratio of same to different trials was varied across three conditions of a “change/no-change” discrimination task. The conditions varied as follows: (a) a ratio of one-third same to two-thirds different trials (33% same), (b) an equal ratio of same to different trials (50% same), and (c) a ratio of two-thirds same to one-third different trials (67% same). Stimuli were synthetic consonant-vowel syllables that changed along a place of articulation dimension by formant frequency transition. Results showed that all subjects changed their response strategies depending on the ratio of same-to-different trials. The most lax response pattern was observed for the 50% same condition, and the most conservative pattern was observed for the 67% same condition. Adult response patterns were most conservative across condition. Differences in discrimination accuracy as measured by P(C) were found, with the largest difference in the 5- to 6-year-old group and the smallest change in the adult group. These findings suggest that children’s response strategies, like those of adults, can be manipulated by changing the ratio of same-to-different trials. Furthermore, interpretation of sensitivity measures must be referenced to task variables such as the ratio of same-to-different trials.

Download Full-text

Author response for "Diabetes alters immune response patterns to acute melioidosis in humans"

10.1002/eji.201848037/v2/response1 ◽

2019 ◽

Author(s):

Barbara Kronsteiner ◽

Panjaporn Chaichana ◽

Manutsanun Sumonwiriya ◽

Kemajitra Jenjaroen ◽

Fazle Rabbi Chowdhury ◽

...

Keyword(s):

Immune Response ◽

Author Response ◽

Response Patterns

Download Full-text

D-test: A New Test for Analyzing Scale Invariance Using Symbolic Dynamics and Symbolic Entropy

Methodology ◽

10.1027/1614-2241/a000026 ◽

2011 ◽

Vol 7 (3) ◽

pp. 88-95 ◽

Cited By ~ 2

Author(s):

Jose A. Martínez ◽

Manuel Ruiz Marín

Keyword(s):

Symbolic Dynamics ◽

Scale Invariance ◽

Rating Scales ◽

Rating Scale ◽

Marketing Research ◽

Response Patterns ◽

Measurement Scales ◽

Improve Measurement ◽

Entropy Measures ◽

The Difference

The aim of this study is to improve measurement in marketing research by constructing a new, simple, nonparametric, consistent, and powerful test to study scale invariance. The test is called D-test. D-test is constructed using symbolic dynamics and symbolic entropy as a measure of the difference between the response patterns which comes from two measurement scales. We also give a standard asymptotic distribution of our statistic. Given that the test is based on entropy measures, it avoids smoothed nonparametric estimation. We applied D-test to a real marketing research to study if scale invariance holds when measuring service quality in a sports service. We considered a free-scale as a reference scale and then we compared it with three widely used rating scales: Likert-type scale from 1 to 5 and from 1 to 7, and semantic-differential scale from −3 to +3. Scale invariance holds for the two latter scales. This test overcomes the shortcomings of other procedures for analyzing scale invariance; and it provides researchers a tool to decide the appropriate rating scale to study specific marketing problems, and how the results of prior studies can be questioned.

Download Full-text

Three Conceptual Impediments to Developing Scale Theory for Formative Scales

Methodology ◽

10.1027/1614-2241/a000154 ◽

2018 ◽

Vol 14 (4) ◽

pp. 156-164 ◽

Cited By ~ 3

Author(s):

Keith A. Markus

Keyword(s):

Scale Development ◽

Item Analysis ◽

Model Fitting ◽

Item Bias ◽

Validity Evidence ◽

Scale Theory ◽

Underlying Theory ◽

Standard Scale ◽

Item Scores

Abstract. Bollen and colleagues have advocated the use of formative scales despite the fact that formative scales lack an adequate underlying theory to guide development or validation such as that which underlies reflective scales. Three conceptual impediments impede the development of such theory: the redefinition of measurement restricted to the context of model fitting, the inscrutable notion of conceptual unity, and a systematic conflation of item scores with attributes. Setting aside these impediments opens the door to progress in developing the needed theory to support formative scale use. A broader perspective facilitates consideration of standard scale development concerns as applied to formative scales including scale development, item analysis, reliability, and item bias. While formative scales require a different pattern of emphasis, all five of the traditional sources of validity evidence apply to formative scales. Responsible use of formative scales requires greater attention to developing the requisite underlying theory.

Download Full-text