When examining self-esteem through the lens of measurement theories, particularly classical test theory (CTT) and item-response theory (IRT), there are distinct differences in how each theory approaches the assessment and interpretation of the self-esteem measure. Classical Test Theory (CTT) focuses on a participant's overall score on a self-esteem measure, positing that each observed score consists of a valid score and an error score (Loevinger, 1957). Reliability is important, as it indicates score consistency across different test administrations. CTT emphasizes group performance averages and item correlations within the scale, suggesting that items should effectively work together to produce a reliable total score. However, CTT does not consider how individual items function at varying levels of self-esteem, primarily concentrating on the aggregate performance of respondents (Thorndike, 2005).
In contrast, Item-Response Theory (IRT) focuses on the relationship between an individual's latent trait (in this case, self-esteem) and their probability of responding correctly (or in a desired manner) to each item on the measure (Embretson & Reise, 2000). IRT considers each item's properties, such as difficulty and discrimination, which allows for a more refined understanding of how different participants interact with the items based on their self-esteem levels (Embretson & Reise, 2000). This theory assesses the performance of each item independently and provides specific insights into how well items discriminate among respondents with various levels of self-esteem. (Embretson & Reise, 2000) Therefore, IRT can produce more refined measures, including ability estimates and graphical representations of individual item functioning on a latent trait scale (Wright & Masters, 1982). In summary, while CTT provides valuable insights through aggregate score reliability and average performance, IRT offers a more individualized approach that analyzes item-level data and allows for a better understanding of the underlying constructs being measured. Each theory has its strengths and considerations when assessing psychological traits like self-esteem.
References
Embretson, S.E., & Reise, S.P. (2000). Item Response Theory for Psychologists (1st ed.). Psychology Press. https://doi.org/10.4324/9781410605269
Loevinger, J. (1957). The assessment of ego development. Journal of Consulting Psychology, 21(6), 626-633.
Thorndike, R. L. (2005). Measurement and Evaluation in Psychology and Education (4th ed.). Upper Saddle River, NJ: Pearson Education.
Wright, B. D., & Masters, G. N. (1982). Rating Scale Analysis. Chicago: MESA Press.