Validity and Reliability Evidence of Professional Obsolescence Scale According to Different Test Theories

Abstract

This study aims to develop a scale that will determine the factors causing professional obsolescence in the field of education. In this context, the Professional Obsolescence Scale (POS) has been developed to determine the professional and organizational obsolescence of primary, secondary and high school administrators. In this scale development process, steps were followed in line with the suggestions of Crocker and Algina (2006) and Cronbach (1984). Firstly, 63 items were prepared and 991 school principals participated the study. R (version 4.0.1) software was used to analyze the data. Item and test parameters and information functions have been estimated using Samejima’s Graded Response Model based on Item Response Theory. Principal Axis Analysis was performed for the construct validity of the scale, and four-dimensions structure with 47 items has been obtained. These dimensions are named as “Being Open to Professional Development”, “Job-Ability Harmony in Profession”, “Organizational Support in Professional Development”, “Professional Burnout”. The scores obtained from each dimension are evaluated within themselves. It has been observed that each dimension fulfills the conditions of unidimensionality, local independence, model-data fit and parameter invariance. According to the Classical Test Theory, Cronbach Alpha coefficients are between 0.807 and 0.945. The Stratified Alpha coefficient calculated for the whole scale is 0.94. According to the Item Response Theory, the marginal reliability coefficients were between 0.857 and 0.936 and the empirical reliability coefficients were found between 0.854 and 0.938.This study aims to develop a scale that will determine the factors causing professional obsolescence in the field of education. In this context, the Professional Obsolescence Scale (POS) has been developed to determine the professional and organizational obsolescence of primary, secondary and high school administrators. In this scale development process, steps were followed in line with the suggestions of Crocker and Algina (2006) and Cronbach (1984). Firstly, 63 items were prepared and 991 school principals participated the study. R (version 4.0.1) software was used to analyze the data. Item and test parameters and information functions have been estimated using Samejima’s Graded Response Model based on Item Response Theory. Principal Axis Analysis was performed for the construct validity of the scale, and four-dimensions structure with 47 items has been obtained. These dimensions are named as “Being Open to Professional Development”, “Job-Ability Harmony in Profession”, “Organizational Support in Professional Development”, “Professional Burnout”. The scores obtained from each dimension are evaluated within themselves. It has been observed that each dimension fulfills the conditions of unidimensionality, local independence, model-data fit and parameter invariance. According to the Classical Test Theory, Cronbach Alpha coefficients are between 0.807 and 0.945. The Stratified Alpha coefficient calculated for the whole scale is 0.94. According to the Item Response Theory, the marginal reliability coefficients were between 0.857 and 0.936 and the empirical reliability coefficients were found between 0.854 and 0.938.