Using Rasch theory to guide the practice of survey development and survey data analysis in science education and to inform science reform efforts: An exemplar utilizing STEBI self‐efficacy data

Abstract

Over many decades, science education researchers have developed, validated, and used a wide range of attitudinal instruments. Data from such instruments have been analyzed, results have been published, and public policies have been influenced. Unfortunately, most science education instruments are not developed using a guiding theoretical measurement framework. Moreover, ordinal-level attitudinal data are routinely analyzed as if these data are equal interval, thereby violating requirements of parametric tests. This paper outlines how researchers can use Rasch analysis to develop higher quality science education instruments and why researchers must use Rasch analysis to prepare appropriate ordinal-level data for parametric analyses. Detailed recommendations are set forth to help science education researchers increase the rigor of attitudinal instrument development and analysis. Suggestions are also set forth regarding how philosophical and analytical Rasch techniques align with broad goals of the science education research community.

Use of the Rasch measurement model to explore the relationship between content knowledge and topic-specific pedagogical content knowledge for organic chemistry

“…Rollnick and Mavhunga (2014) reported a correlation of 0.54 for a study on electrochemistry in which the Rasch analysis was done for only one of the scales, namely the TSPCK data. Neither of these studies involved the transformation of both CK and TSPCK data to linear measures as recommended by Boone et al (2011). Jüttner et al (2013) used the Rasch method in order to estimate the correlation of biology teachers' CK and PCK to a higher level of precision.…”

“…Applying the Rasch model can enhance the quality of a project at various levels. The rigour of analysis is increased and the assumption of linearity can be met -an assumption often ignored in the analysis of educational data (Boone & Rogan, 2005, Boone et al, 2011). …”

“…The development of a quality instrument that probes a specific trait in a comprehensive manner requires both qualitative and quantitative thought and reflection (Boone et al, 2011). The researcher must have a thorough understanding of the theory underpinning the trait and its expected manifestations so that varying strengths of the trait can be captured on a scale of "less than" to "more than" along a single dimension.…”

Quality Assessment in Video Surveillance

“…A more formal way toward validation of subjects is the Rasch theory (Boone et al, 2010). It defines the difficult level for each particular question (e.g.…”

“…Moreover, the more subjects involved in the test, the higher the accuracy of the method. An excellent example of this methodology in use is national high school exams, where the Rasch theory helps in detecting the differences between different boards marking the pupils' tests (Boone et al, 2010). In subjective experiments, there are always limited numbers of answers per question.…”