What is the historical context for measurement?
Research has shown that attitude toward the subject plays a major role in students’ learning and retention. Students tend to perform better in the classroom when they are interested, and engaged, in the material. Therefore, there is a continual need for statistics educators to engage in research surrounding affective constructs, or how students perceive statistics. Affective constructs can include the attitudes, beliefs, emotions, dispositions, and motivations of the student and/or instructor (Pearl et al, 2012). There are inevitably some challenges associated with accurately measuring attitudes and beliefs. Affective constructs are hard to measure, tend to be subjective, and can lead to counterintuitive results due to the wording of the question and the presence of confounding variables. However, through the work of many dedicated researchers and practitioners, the methods and surveys used to measure students’ and teachers’ attitudes toward statistics have been refined and validated throughout the years.
What might measurement look like in the classroom?
- Using one of the validated instruments both at the beginning and at the end of the course to measure the change in students’ attitudes toward statistics throughout the course
- Using one of the validated instruments at the end of the course to measure students’ attitudes toward statistics and data science to refine the curriculum to make it more relevant and engaging for students
- Using one of the validated instruments mid-way through the course to determine which aspect of students’ attitudes toward statistics needs to be targeted for the remainder of the course
What research on measurement has been done?
Work on affective constructs, and students’ attitudes toward statistics, has been conducted since as early as the 1980’s. Beginning with the Statistics Attitude Survey (SAS), and subsequently the Attitudes Toward Statistics (ATS), researchers were active in trying to establish some relationship between students’ attitudes toward the subject and their performance in the course. The most reputable measurement tool to come out of this era, and the one that is still referenced and studied decades later, is the Survey of Attitudes Toward Statistics (the initial SATS-28 and the expanded SATS-36). This survey consists of items addressing affect, cognitive competence, value, difficulty, interest, and effort components (Bateiha, Marchionda and Autin, 2020). There have been countless studies over the years that have used and/or validated the use of the SATS. However, contrary to what intuition may suggest, many of the studies have had inconclusive or mixed results. In fact, measurements that stay relatively constant can be good evidence in this realm. Sometimes the results may even show a small decrease in attitude, which could be due to any number of factors, including students’ perception of question wording or misunderstanding of the scale being used (Bond, Perkins, and Ramirez, 2012). One study that found promising results regarding attitudes toward statistics was conducted by Joan Garfield, Bob delMas and Andy Zieffler. Using the Affect Survey, a measurement tool developed by these researchers, they found that students tend to have a positive attitude toward statistics and find software useful for achieving the learning objectives of the course (Garfield, delMas and Zieffler, 2012).
Since the creation, and expansion, of the SATS, there has not been much research conducted on competing measurement tools. On the discussion of affective constructs, the SATS is still the most frequently referenced family of assessment tools for measuring these constructs in the statistics classroom. Although there are many strengths of the SATS, as with any instrument, it has its limitations. With the onset of the pandemic and the transition to online learning, there has been an increased interest in the role that attitude plays in a student’s learning experience. Also, given the rise in popularity of data science in recent years, there is a newfound concern for the fact that there is currently no validated instrument used to measure students’ attitudes toward data science. As a result, a research team led by Douglas Whitaker, Alana Unfried, and Marjorie Bond, has been very active lately in conducting research on this topic, both by addressing challenges with using the SATS to measure students’ statistics attitudes and proposing the S-SOMAS instrument as a viable alternative for measuring student and instructor attitudes toward both statistics and data science (Whitaker, Unfried and Bond, 2019; Whitaker, Unfried and Bond, 2022). The eventual goal would be for this instrument to be widely disseminated for use by statistics and data science educators alike. There is an ever-growing need for statisticians and data scientists in the workforce, and thus, it is imperative for educators to foster a positive attitude toward statistics and data science to produce qualified candidates to adequately fill this demand.
What are some ideas or research questions for starting to explore measurement?
- Investigate whether students have a more positive attitude toward statistics after taking an SBI-methods course as compared to a traditional course
- Measure whether students’ attitude toward statistics and/or data science improves throughout the course
- Investigate the relationship between the various subscale scores (e.g., affect and interest)
- Study whether similar patterns in responses (i.e., no change, or even a slight decrease, in attitude) are observed in other disciplines as well
- Expand the typical pre-course and post-course survey style to have follow-up surveys to see if attitude toward the subject changes over time
- Investigate the relationship between students’ attitudes toward statistics and students’ attitudes toward mathematics
- Study the relationship between demographic characteristics and student attitudes toward statistics and data science
What are some prominent measurement tools that have been developed?
| Measurement Tool | Author | Description | Who to Contact to Gain Access |
|---|---|---|---|
| Survey of Attitudes Toward Statistics (SATS) | Candace Schau | Tool for measuring student attitudes toward statistics | Register at the following link: https://www.evaluationandstatistics.com/register to request access to the SATS tool |
| The Affect Survey | Joan Garfield, Bob delMas and Andy Zieffler | Tool for measuring students’ attitudes about the course (what they gained from it, their perspective on statistics, etc.) | Any requests for this tool should be directed to the author(s) |
| S-SOMAS & S-SOMADS, I-SOMAS & I-SOMADS | Douglas Whitaker, Alana Unfried and Marjorie Bond | Tool for measuring student and instructor attitudes toward both statistics and data science | Not available for access yet |
What are the best practices to follow when using a measurement tool?
- As a general rule of thumb, be sure to use the full instrument, not individual items, when implementing an instrument in your classroom.
- The reliability, validity, and fairness measures that validate the use of the instrument are on the aggregate amount of items, not on the individual items.
- Always ask for permission from the author(s) before using an instrument in your classroom.
- When in doubt, it is always best to reach out to the author(s) of the instrument to receive permission for use and/or access to their instrument
Key Articles (as cited throughout)
Early Research on Measurement
- Bond, M. E., Perkins, S. N., & Ramirez, C. (2012). Students’ perceptions of statistics: An exploration of attitudes, conceptualizations, and content knowledge of statistics. Statistics Education Research Journal, 11(2), 6–25. https://doi.org/10.52041/serj.v11i2.325
- Pearl, D., Garfield, J., del Mas, R. C., Groth, R. E., Kaplan, J. J., McGowan, H., & Lee, H. S. (2012). Connecting research to practice in a culture of assessment for introductory college-level statistics. https://www.causeweb.org/cause/archive/research/guidelines/ResearchReport_2012.pdf
- Garfield, J., delMas, R., & Zieffler, A. (2012). Developing statistical modelers and thinkers in an introductory, tertiary-level statistics course. ZDM, 44(7), 883–898. https://doi.org/10.1007/s11858-012-0447-5 (Links to an external site.)
Late Research on Measurement
- Whitaker, D., Unfried, A., & Bond, M. (2019). Design and Validation Arguments for the Student Survey Of Motivational Attitudes toward Statistics (S-SOMAS) Instrument. In J. D. Bostic, E. E. Krupa, & J. C. Shih (Eds.), Assessment in Mathematics Education Contexts: Theoretical Frameworks and New Directions (1st ed.). Routledge.
- Bateiha, S., Marchionda, H., & Autin, M. (2020). Teaching style and attitudes: A comparison of two collegiate introductory statistics classes. Journal of Statistics Education, 28(2), 154–164. https://doi.org/10.1080/10691898.2020.1765710
Whitaker, D., Unfried, A., & Bond, M. (2021). Challenges Associated with Measuring Attitudes Using the SATS Family of Instruments. Statistics Education Research Journal, 21(1). https://iase-web.org/ojs/SERJ/article/view/88
The CAUSE Research Group is supported in part by a member initiative grant from the American Statistical Association’s Section on Statistics and Data Science Education