Avoiding Over-Diagnosis: Exploring the Role of Gender in Changes over Time in Statistics Anxiety and Attitudes

Abstract

The importance of quantitative literacy for creating and maintaining a democratic and just society is unequivocal, but undergraduate students often do not acquire these important skills. One barrier to teaching quantitative literacy skills is students' anxiety. The empirical evidence of the extent of the problem, however, does not seem to match anecdotal accounts of instructors who may be "diagnosing" statistics anxiety as universal among students and across different sources of anxiety. The purpose of this study is to identify the specific aspects of statistics anxiety that present barriers to student success by employing the Statistics Anxiety Rating Scale (STARS) to analyze two-wave panel survey data from a sample of 113 undergraduates from eight sections of a Social Statistics course. This study also examines how gender shapes statistics anxiety/attitudes and whether changes over time in anxiety/attitudes are associated with academic performance. Results indicate that a majority of students report elevated levels of exam anxiety compared to the other types of anxiety/attitudes. Women report significantly more anxiety and more negative attitudes than men, but exam anxiety improves over the course of the semester significantly more so for women. Results also indicate that statistics anxiety/attitudes are largely unrelated to academic performance. Results are discussed in the context of their implications for directing attention to specific aspects of statistics anxiety on which to focus pedagogical efforts-to address statistics anxiety/attitudes if necessary, but also to avoid over-diagnosing by not assuming that it applies to all students or all aspects of statistics classes.Another contribution this study makes to the literature on statistics anxiety is examining variation in the levels/types of anxiety and changes over time by gender. Research that has examined gender differences show inconsistent findings, with some studies finding a greater degree of statistics and math anxiety among women compared to men (Benson 1989;Bradley and Wygant 1998;Onwuegbuzie 1998;DeCesare 2007;Condron et al. 2018), while other studies show mixed or no gender differences

Statistical anxiety and attitudes towards statistics: Criterion-related construct validity of the HFS-R questionnaire revisited using Rasch models

“…In addition to this, they also provided evidence of gender differences on the Test and Class Anxiety and the Interpretation Anxiety subscales, with the female students obtaining the highest scores. More recently, a small-sample study of MacArthur (2020) found differences between male and female undergraduate social science students attending an introductory course on statistics. Here female students scored higher than males on Test and Class Anxiety as well as Interpretation Anxiety one week into course, but they found no differences at the end of the semester.…”