Printer Friendly

Statistics anxiety: antecedents and instructional interventions.

Competency in statistics is an integral component of the scientific method and has contributed enormously to the amount and sophistication professional knowledge within the academic disciplines. Despite these contributions, the value of statistics varies widely in the general population. On one hand, Davenport and Harris (2007) describe the essential importance of statistics by referencing the father of statistics, C. Edward Deming (1900-1993): In God we trust; all others bring data. Yet, Smith (2010) references a skeptical view of statistics popularized by Mark Twain (1835-1910): There are three kinds of lies: lies, damned lies, and statistics.

Despite these widely divergent views, many students approach the study of statistics with much fear, trepidation and anxiety. Indeed, a random survey of students entering a graduate-level education program rated the course requirement in statistics as the least desirable of all courses required for their academic major (Dykeman, 2010), and approximately 75% to 80% of graduate students in the social sciences appear to experience uncomfortable levels of statistics anxiety which negatively affect learning (Onwuegbuzie, Slate, et al., 2000; Onwuegbuzie & Seaman, 1995).

Many students delay taking statistics until the very end of their required curriculum. Yet, the successful understanding of statistics contributes enormously to the development of critical thinking skills needed to evaluate the professional literature presented in the social science and professional education curriculum.

The pedagogy of statistics is an active concern of statistics educators, and this pedagogy includes a variety of topics of crucial concern to the development of student competency. A survey of 162 articles in three journals of statistics education from 2005 through 2009 indicated the following topics, with percentages of total topic presentations indicated in parentheses (van der Merwe & Wilkinson, 2010): teaching and learning (29%), statistical reasoning (25%), computer use (15%), course design (12%), non-cognitive factors (10%), and non-empirical studies (9%). As noted, studies in the pedagogy of statistics education are directed to the (1) content of statistical analysis, (2) use of computers and software for statistical analysis, (3) teaching and learning strategies, and (4) non-cognitive factors that can either help or hinder student acquisition of skills needed to perform statistical analysis.


Students come to their course work in statistics with varying degrees personality dispositions and academic experiences that can either help or hinder their ability to do well. The antecedents of statistics anxiety are described in Balogly's (2001) structural equation modeling of 246 university students: (1) dispositional factors, such as perceived task difficulty and degree of ego threat; (2) situational factors, such as the immediate factors surrounding the stimulus events; and (3) environmental factors, such as age, gender and relevant background experience. These antecedents influence the amount of trait anxiety brought to the study of statistics by each student as well as the state anxiety each student experiences when responding to stressors in their immediate situation. Dispositional and environmental factors interact with situational stressors to produce varying amounts of facilitative and debilitative anxiety (Alpert & Haber, 1960). Indeed, high-anxiety students in high-stress evaluative conditions demonstrate more emotionality and poorer performance than students in either high anxiety-low stress, low anxiety-high stress, or low anxiety-low stress conditions (Deffenbacher, 1978). In this regard, student responses to the stress induced by the study of statistics will vary widely, yet many students look upon the study of statistics as a high-stress condition and will avoid or delay their required statistics class during their academic studies.

The study of statistics anxiety has emanated from studies on anxiety, attitude, efficacy, and math experience. Measures of statistics anxiety and attitude toward statistics have been found to be highly correlated (Mji & Onwuegbuzie, 2004; Zeidner, 1991), yet subtle differences exist. For instance, Cruise, Cash and Bolton (1985) published the Statistics Anxiety Rating Scale (STARS) comprised of (a) perceived worth of statistics, (b) interpretation anxiety, (c) test and class anxiety, (d) conceptual sell-concept, (e) fear of asking for help and (f) fear of the statistics teacher; while Zeidner (1991) developed the Statistics Anxiety Inventory (SAI), which is comprised of (a) statistics content anxiety and (b) statistics test anxiety. In contrast, Wise (1985) developed the Attitude Toward Statistics (ATS) scale that measures (a) attitude towards the course and (b) attitude towards the field; while Shau et al. (1995) developed the Survey of Attitudes Toward Statistics (SATS), which measures (a) affect, (b) cognitive competence, (c) perceived value of statistics and (d) perceived difficulty. Despite the subtle differences, the constructs of anxiety and attitude share many characteristics, including the efficacy to do well in statistics and the math experience one has acquired before taking a course in statistics. For instance, Schacht & Stewart (1990) establish the relationship between the lack of self-efficacy and the reluctance to engage in research, and Pan and Tang (2005) discuss the relationship between statistics anxiety and the fear of failure. Onwuegbuzie and Wilson (2003) present relationships between statistics anxiety and prior experience with mathematics, statistics, computer use and research.


The purpose of this study was to explore differences in levels of course anxiety and academic self-efficacy between students taking a course in statistics and with students taking other education courses. Additionally, this study looked at differences in the distribution of scores across measurements on anxiety, attitude, self-reported readiness, and expectation-for-success for statistics students with and without prior course work in statistics.

For purposes of this study, statistics anxiety is defined as anxiety that occurs as a result of encountering statistics in any form and at any level (Onwuegbuzie, DaRos, & Ryan, 1997). In this regard, the anxiety of statistics can affect students when studying at home or in class, when reading about statistics or doing a statistics problem, or when taking a statistics test; and the effects of anxiety can be manifested through physiological, psychological and behavioral expressions.


Fifty-seven students at a urban Midwestern university enrolled in course work leading to professional degrees in education participated in the study, with 37 students enrolled in a statistics course compared to 20 students in other education courses on measures of course anxiety and academic self-efficacy. Measures included adaptations of the Achievement Anxiety Scale (Alpert and Haber, 1960) to assess facilitative and debilitative anxiety and the General Self-Efficacy Scale (Schwarzer & Jerusalem, 1995) to assess perceived efficacy to do well in class. Then, the 37 students taking course work statistics completed the Statistics Anxiety Measure (Earp, 2007) to compare differences on measures of anxiety, attitude, self-reported readiness and expectation between students with (n = 22) and without (n = 15) prior statistics course work.

Students taking university course work in statistics were compared to students taking other education classes on measures of anxiety and academic self-efficacy. An SPSS data analysis for independent groups was used for two-tailed significance testing. Statistics students demonstrated higher levels debilitative anxiety, t(1,55) = 2.155, p < .05, and lower levels of academic self-efficacy than other education students, t(1,55) = 2.898, p < .01. No significant difference was noted between statistics and non-statistics students on a measure of facilitative anxiety, t(1,55) = 1.769, p = .082.

Students taking a course in statistics with and without prior course work in statistics were compared on measures of self-reported readiness, anxiety, attitude and expectation to do well in the statistics course. A multivariate SPSS data analysis for independent groups indicated a significant difference on simultaneous measures of anxiety, self-rated readiness, attitude and expectation to do well, Wilks' (4,32) = 3.02, p <.05. Students with prior course work in statistics demonstrated higher levels of anxiety, t(1,35) = -3.64, p < .01, more self-rated readiness, t(1,35) = +2.52, p < .05, and lower expectation to well in the course, t(1,35) = +2.49, p < .05, than students with no prior course work in statistics. Students with prior course work in statistics did not differ from students without prior course work on a measure of attitudes toward the course, t(1,35) = 1.00, p = .316.


The study of statistics is a requirement for students pursuing academic degrees in professional education, yet students vary considerably in their preparation for this course. Some students come with prior course work in the study of statistics, yet others have neither prior course work nor study in the quantitative sciences that can give adequate preparation for statistics education. To this end, students come to the study of statistics with much variability in their anxiety, self-rated readiness, and self-efficacy to do well.

The van der Merwe and Wilkinson (2010) three-year literature review of statistics education journals indicated that 25 percent of all articles pertained to issues of teaching and learning, with 10 percent pertaining to non-cognitive factors of student learning. To this end, the pedagogy of statistics education includes much discussion about the instructional strategies of enhancing student acquisition of competencies in statistics as well as the strategies of reducing non-cognitive factors that could interfere with that acquisition.

Strategies available to statistics instructors to reduce debilitative anxiety and improve self-confidence have been reported in the literature, and this literature has focused on activities both within and outside the classroom setting. To this end, Dolinsky (2001) recommended instructors to create a collaborative classroom environment in which active learning strategies are used as an integral component of instruction, and the Pan and Tang's (2004) study showed that a combination of application-oriented teaching with instructor availability improved student attitudes toward statistics education. Forte (1995) argued for a teaching approach that incorporated computer usage, real-world applications, humor, statistical language practice, and group-learning principles. Schacht and Stewart (1990) found that the use of relevant and humorous cartoons reduced anxiety and improved concentration on the topic of study. Sgoutas-Emch and Johnson (1998) reported that journal writing about the content learned in statistics classes reduced much of the anxiety students bring with them to class. Pan and Tang (2005) reported results of a student focus group that identified recommendations for reducing anxiety, including (a) an orientation letter sent to students a week prior to the class to discuss course expectations and the required background knowledge in math, along with textbook information and available resources for help if students had any concerns or questions; (b) an instructor who maintains flexible and extra office hours, (c) an interim class survey that addresses the students' concerns; (d) permitting students to bring a note sheet to the final exam and (e) an option to take the course on a Pass/Fail basis as an alternative to the regular letter grading system. An informal survey within this current study included (a) opportunities to discuss the meaning vocabulary used in statistics education, (b) narrative and graphical illustrations of statistics equations, and (c) multiple, non-graded tests to develop familiarity with testing format and response options (Dykeman, 2010).

Approximately 75 to 80 percent of graduate students in the social sciences are estimated to experience uncomfortable levels of statistics anxiety, which negatively affects learning (Onwuegbuzie, Slate, et al., 2000). Results from this study substantiate these previous findings and show that the type of academic anxiety experienced by students taking statistics is different from the anxiety of students in other courses. In addition, students without previous course work in statistics come to their course with higher levels of anxiety, lower self-perceived readiness, and lower self-efficacy than students with no prior course experience. Indeed, there is much variability in student preparation for statistics education, with some students well-prepared and others feeling ill-prepared and anxious. To this end, instructors can implement a number of instructional strategies to reduce anxiety and improve the self-confidence necessary to do well in their statistics courses.


Alpert, R. & Haber, R.N. (1960). Anxiety in academic achievement situations. Journal of Abnormal and Social Psychology, 61, 207-215.

Cruise, R.J., Cash, R.W. & Bolton, D.L. (1985). Development and validation of an instrument to measure statistical anxiety. Proceedings of the Statistical Education Section of American Statistical Association, Washington, DC.

Davenport. T.H. & Harris, J.G. (2007). The new science of winning. Boston, MA: Harvard Business School Press.

Deffenbacher, J. L. (1978). Worry, emotionality, and task-generated interference in test anxiety: An empirical test of attentional theory. Journal of Educational Psychology, 70(2), 248-254.

Dolinsky, B. (2001). An active learning approach to teaching statistics. Teaching of Psychology 28, 55-56.

Dykeman, B. (2010). Unpublished survey of student attitudes toward statistics education. Chicago, IL: Roosevelt University.

Earp, M.S. (2007). Development and validation of the Statistics Anxiety Measure. Retrieved from tions/dissertations/07.Earp.Dissertation.pdf.

Forte, J. A. (1995). Teaching statistics without sadistics. Journal of Social Work Education, 31, 204-218.

Mji, A. & Onwuegbuzie, A.J. (2004). Evidence of score reliability and validity of the Statistical Anxiety Rating Scale among Technikon students in South Africa. Measurement and Evaluation in Counseling and Development, 36, 238-251.

Onwuegbuzie, A. J., Slate, J.R., Paterson, F.R., Watson, M.H. & Schwartz, R.A. (2000). Factors associated with achievement in educational research courses. Research in the Schools, 7, 53-65.

Onwuegbuzie, A.J., DaRos, C., & Ryan, J.M. (1997). The components of statistics anxiety: a phenomenological study. Focus on Learning Problems in Mathematics, 19(4), 11-35.

Onwuegbuzie, A. J. & Seaman, M. (1995). The effect of time and anxiety on statistics achievement. Journal of Experimental Psychology, 63, 115-124.

Onwuegbuzie, A. J. & Wilson, V. A. (2003). Statistics anxiety: Nature, etiology, antecedents, effects, and treatments: A comprehensive review of the literature. Teaching in Higher Education, 8, 195-209.

Pan, W. & Tang, M. (2004). Examining the effectiveness of innovative instructional methods on reducing statistics anxiety for graduate students in the social sciences. Journal of Instructional Psychology, 31, 149-159.

Pan, W. & Tang, M. (2005). Students' perceptions on factors of statistics anxiety and instructional strategies. Journal of Instructional Psychology, 32, 205-214.

Schacht, S. & Stewart, B.J. (1990). What's funny about statistics? A technique for reducing student anxiety. Teaching Sociology, 18, 52-56

Schwarzer, R. & Jerusalem, M. (1995). Generalized Self-Efficacy Scale. In J. Weinman, S. Wright, & M. Johnston, Measures in health psychology: A user's portfolio: Causal and control beliefs (pp. 35-37). Windsor, England: Nelson Publishing.

Schau, C., Stevens, J., Dauphinee, T. & Del Vecchio, A. (1995). The development and validation of the Survey of Attitudes Toward Statistics. Educational & Psychological Measurement, 55 (5), 868-876.

Sgoutas-Emch, S.A. & Johnson, C.J. (1998). Is journal writing an effective method of reducing anxiety towards statistics? Journal of Instructional Psychology, 25, 49-57.

Smith, H.E. (Ed.) (2010). The autobiography of Mark Twain, Vol. 1. Berkeley, CA: University of California Press.

Wise, S.L. (1985). The development and validation of a scale measuring attitudes toward statistics. Educational and Psychological Measurement, 45, 401-405.

Zeidner, M. (1991). Statistics and Mathematics Anxiety in Social Science Students: Some Interesting Parallels. British Journal of Educational Psychology, 61, 319-328.


Department of Specialized Studies, Roosevelt University.
COPYRIGHT 2011 Project Innovation (Alabama)
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2011 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Author:Dykeman, Bruce F.
Article Type:Report
Date:Dec 22, 2011
Previous Article:Clashing values: contemporary views about cheating and plagiarism compared to traditional beliefs and practices.
Next Article:What informs teachers' views: the Vietnam War as a case study in the era of standardization.

Terms of use | Privacy policy | Copyright © 2019 Farlex, Inc. | Feedback | For webmasters