Illustration of a Survey Refinement Process Using Psychometric Analysis

• In Event: 32.080 - Measurement and Validity Issues in Survey Research

Abstract

Questionnaire refinement and a process for selecting items for elimination are important tools for survey developers. One of the major obstacles in questionnaire refinement and elimination in surveys lies in one’s ability to adequately and appropriately reconstruct a survey. Often times, surveys can be long and strenuous on the respondent, resulting in lower response rates and questioned validity of responses, particularly for items appearing later in the survey. Therefore, tailored assessments with less questions are desired. This paper illustrates a process using psychometric information to reduce the length of a survey while maintaining reliability of the measure. The procedures used in this work are accessible to survey developers with background in psychometrics and basic knowledge of R programming.

Authors

• William Zachary Smith, University of South Carolina - Columbia

• Tammiee S. Dickenson, University of South Carolina - Columbia

• Bradley David Rogers, University of South Carolina