Saturday, 15 January 2005 - 8:00 AM

This presentation is part of: Social Work Education and Practice

The use of Classical Measurement Theory, Item Response Theory and Generalizability Theory in the validation of the Corporate Behavioral Wellness Screening Inventory for use in educational settings

The Corporate Behavioral Wellness Screening Inventory (CBWSI) was originally designed and validated for use within public health organizations as an instrument that can holistically capture organizational wellness, social/team support, and the personal wellness of service providers. The original version of the CBWSI was developed and validated on a sample of 1040 employees from diverse organizations. Psychometric analyses, based on Classical Measurement Theory, indicated the CBWSI to be a reliable and valid scale. The Cronbach alphas ranged between .78 and .95 (mean alpha = .86); the standard error of measurement (SEM) ranged between 1.21 and 3.02 (mean SEM = 2.27). The content validity showed a mean failure rate of 0.14% and a mean success rate of 99.86% across all subscales. As an indication of discriminant construct validity, the background variables showed a mean correlation of .09 across the different subscales.

With this research as background, a new study was conducted to adapt the CBWSI for use within educational settings to measure the wellness of faculty in their role as teachers. A representative, national sample of 650 faculty at Master’s level, accredited schools of social work took part in this research. This paper will focus on the changes made to the CBWSI and on the psychometric data available on this revised scale. In addition to the basic psychometric analyses done on the revised CBWSI, other measurement theories were also applied. Specifically, Item Response Theory was used to test how the instrument performed at different levels of the measured construct. Relatedly, Generalizability Theory was used to test the dependability of the clinical cutting scores developed in previous studies. This paper provides an applied example illustrating the complimentary relationship among Classical Measurement Theory, Item Response Theory, and Generalizability Theory when each are used in the process of scale development and validation.

See more of Social Work Education and Practice
See more of Oral and Poster

See more of Celebrating a Decade of SSWR (January 13 - 16, 2005)