Assessing Changes in Students' Attitudes: The Good, the Bad, and the Ugly

• Activity Number: 506
• Type: Topic Contributed
• Date/Time: Wednesday, August 4, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistical Education
• Author(s): AnneMichele Millar*+ and Candace Schau
• Companies: Mount Saint Vincent University and CS Consultants, LLC
• Keywords: statistics education ; Survey of Attitudes toward Statistics ; SATS ; students' attitudes ; pre-post change

Abstract

Many statistics instructors and statistics education researchers are interested in how students' attitudes change across statistics courses from beginning (pretest) to end (posttest). There are a variety of types of scores and analysis methods used to assess pretest-posttest change. These include, for example, gain scores, residual posttest scores freed from pretest influences using covariance, and latent growth models. Our paper evaluates selected types of scores and analysis methods to compare the results in terms of statistical significance, effect sizes, and confidence intervals. Although we use component scores from the Survey of Attitudes toward Statistics for our evaluation, our work applies to other types of student outcomes including, for example, achievement.