Using the Many-Facet Rasch Model to Evaluate the Psychometric Quality of Teacher Sense of Efficacy Scale

• In Event: Evaluating the Psychometric Quality of Self-Efficacy Measures With Diverse Item-Analysis Methods

Abstract

Purpose and Theoretical Framework

A teacher’s sense of efficacy refers to beliefs in one’s capability to organize and execute courses of action required to successfully accomplish specific teaching tasks in a particular context (Tschannen-Moran & Woolfolk Hoy, 2001). A strong sense of efficacy is related to enthusiasm, higher motivation, and resilience across the span of a teaching career (Tschannen-Moran, Woolfolk Hoy, & Hoy, 1998). Moreover, several studies have found that higher levels of burnout are related to lower teacher efficacy or work achievement (Blase, 1982; Brouwers, Evers, & Tomic, 1999; Friedman & Farber, 1992).
Despite the promising path in teacher efficacy studies, several researchers have raised concerns for its psychometric problems in teacher efficacy measures (Henson, 2002; Klassen et al., 2011; Tschannen-Moran et al. 1998). Relatively few studies have used modern model-based measurement (Embretson, 2010), such as the Rasch model (Rasch 1960/1980), to evaluate the psychometric quality of the self-efficacy instruments.
The purpose of this study is to illustrate the use of Rasch measurement theory for evaluating the psychometric quality of Teachers’ Sense of Efficacy scale (Tschannen-Moran & Woolfolk Hoy, 2001). A Many Facet Rasch Model (MFRM) was used to examine relationships of teacher sense of self-efficacy with three explanatory variables: years of teaching experience, schools location, and self-reported degree of burnout.
The theoretical framework for the psychometric analyses is based on the work of Rasch (1960/1980). The following MFRM is used:

Ln (Pnijlmk / Pnijlmk -1) = θn – δi – Δj – αl – βm –τik [1]
where
Pnijlmk = the probability of student n responding in category k on item i ,
Pnijlmk-1 = the probability of student n responding in category k-1 on item i ,
θn = the sense of self-efficacy for teacher n,
δi = the location of item i.
Δj = years of teaching experience j,
αl = school location l,
βm = degree of burnout m, and
τk = the difficulty of responding in category k relative to k-1 on the rating scale

Methods

Participants were 554 in-service teachers from a Midwestern state in the United States (39.1% in urban schools, 29.9% in suburban schools, and 25.2% in rural schools). An adapted version the Teacher’s Sense of Efficacy Scale (TSES; Tschannen-Moran and Woolfolk Hoy, 2001) and Maslach Burnout Inventory-Educator Survey scale (MBI-ES, Maslach & Jackson, 1981) were used to measure teacher sense of self-efficacy and the psychological syndrome of burnout.

Preliminary Results

The preliminary Rasch analyses are summarized in Table 1. Figure 1 presents the variable map for the teachers and the TSES items. Figure 2 shows the variable map for the TSES items, teaching experiences, location of the schools, and degree of burnout.

Scientific Significance

Self-efficacy has emerged as a key construct for understanding human behavior in a variety of contexts. The measurement of this concept with a strong model-based theory, such as Rasch measurement theory, promises to strengthen our understanding of the construct of self-efficacy.

Authors

• Mei-Lin Chang, Emory University

• George Engelhard, Emory University