Validating a developmental scale for young children using the Rasch model: applicability of the teaching strategies GOLD assessment system

J Appl Meas. 2014;15(4):405-21.

Abstract

This article reports the results of an application of the Rasch rating scale model to the Teaching Strategies GOLD assessment system in a norm sample of children aged birth to 71 months. The analyses focused on the examination of dimensionality, rating scale effectiveness, the hierarchy of item difficulties, and the relationship of developmental scale scores to child age. Results show that each subscale satisfies the Rasch model for unidimensionality. Ratings were found to be less reliable at the lowest and highest ends of the scale and less distinct at 'In-between' levels. Items appear to form theoretically expected hierarchies, supporting evidence for construct validity for the measures. Moderately high correlations of developmental scale scores with child age suggest that teachers are able to make valid ratings of the developmental progress of children across the intended age range.

Publication types

  • Evaluation Study
  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Child Development / classification*
  • Child, Preschool
  • Educational Measurement / methods*
  • Educational Measurement / statistics & numerical data
  • Faculty / statistics & numerical data*
  • Female
  • Humans
  • Infant
  • Infant, Newborn
  • Male
  • Models, Statistical*
  • North Carolina
  • Professional Competence / statistics & numerical data*
  • Psychometrics / methods*
  • Psychometrics / statistics & numerical data
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Teaching / statistics & numerical data