statistics anxiety

This article was downloaded by:[The University of Iowa]On: 7 January 2008Access Details: [subscription number 785026722]Publisher: RoutledgeInforma Ltd Registered in England and Wales Registered Number: 1072954Registered office: Mortimer House, 37-41 Mortimer Street, London W1T 3JH, UK

Teaching in Higher EducationPublication details, including instructions for authors and subscription information:http://www.informaworld.com/smpp/title~content=t713447786

Statistics Anxiety: nature, etiology, antecedents, effects,and treatments--a comprehensive review of theliteratureAnthony J. Onwuegbuzie a; Vicki A. Wilsona Department of Human Development and Psychoeducational Studies, HowardUniversity, 2441 Fourth Street, Washington DC, 20059, USA Education Department,Muskingham College, New Concord, OH 43762, USA.

Online Publication Date: 01 April 2003To cite this Article: Onwuegbuzie, Anthony J. and Wilson, Vicki A. (2003) 'StatisticsAnxiety: nature, etiology, antecedents, effects, and treatments--a comprehensivereview of the literature', Teaching in Higher Education, 8:2, 195 - 209To link to this article: DOI: 10.1080/1356251032000052447

URL: http://dx.doi.org/10.1080/1356251032000052447

PLEASE SCROLL DOWN FOR ARTICLE

Full terms and conditions of use: http://www.informaworld.com/terms-and-conditions-of-access.pdf

This article maybe used for research, teaching and private study purposes. Any substantial or systematic reproduction,re-distribution, re-selling, loan or sub-licensing, systematic supply or distribution in any form to anyone is expresslyforbidden.

The publisher does not give any warranty express or implied or make any representation that the contents will becomplete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should beindependently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings,demand or costs or damages whatsoever or howsoever caused arising directly or indirectly in connection with orarising out of the use of this material.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08

Teaching in Higher Education, Vol. 8, No. 2, 2003, pp. 195209

Statistics Anxiety: nature, etiology,antecedents, effects, andtreatmentsa comprehensivereview of the literatureANTHONY J. ONWUEGBUZIE* & VICKI A. WILSON*Department of Human Development and Psychoeducational Studies, HowardUniversity, 2441 Fourth Street, Washington DC, 20059, USA and EducationDepartment, Muskingham College, New Concord, OH 43762, USA

ABSTRACT Most college students are required to enroll in statistics and quantitative researchmethodology courses as a necessary part of their degree programmes. Unfortunately, manystudents report high levels of statistics anxiety while enrolled in these classes. Recent years haveseen an increase in the number of articles on statistics anxiety appearing in the literature, asresearchers have recognised that statistics anxiety is a multidimensionality construct that hasdebilitative effects on academic performance. Thus, the purpose of this article is to provide acomprehensive summary of the literature on statistics anxiety. In particular, the nature,etiology, and prevalence of statistics anxiety are described. Additionally, antecedents (i.e.dispositional, situational and environmental) of statistics anxiety are identified, as well as theireffects on statistics achievement. Furthermore, existing measures of statistics anxiety aredocumented. Finally, based on the literature, successful interventions for reducing statisticsanxiety are described. Implications for future research are provided.

As the need for the application of statistical techniques has increased over the years,so more college students are required to enroll in statistics courses as a necessarypart of their degree programmes. Because many of these students come from diverseacademic backgrounds, some of which appear far removed from the field of statis-tics, taking a statistics course is often a negative experience. Interestingly, Lalondeand Gardner (1993), Lazar (1990), and Onwuegbuzie (in press b) suggest thatlearning statistics is similar to learning a foreign language. Consequently, manystudents report high levels of anxiety while enrolled in statistics courses.

According to Onwuegbuzie (in press a), between two-thirds and four-fifths ofgraduate students appear to experience uncomfortable levels of statistics anxiety.Indeed, for many students, statistics is one of the most anxiety-inducing courses intheir programmes of study (Caine et al., 1978; Lundgren & Fawcett, 1980; Blalock,1987; Gaydosh, 1990; Schacht & Stewart 1990, 1991; Zeidner, 1991). The levels of

ISSN 1356-2517 (print)/ISSN 1470-1294 (online)/03/020195-15 2003 Taylor & Francis LtdDOI: 10.1080/1356251032000052447

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08

196 A. J. Onwuegbuzie & V. A. Wilson

statistics anxiety experienced by students can be so great that undertaking statisticsclasses has come to be regarded by many as extremely negative (Onwuegbuzie,1997a), and perhaps, more importantly, a major threat to the attainment of theirdegrees. In fact, as a result of anxiety, students often delay enrolling in statisticscourses for as long as possible, sometimes waiting until the final semester of theirdegree programmeswhich is clearly not the optimal time to undertake suchcourses (Onwuegbuzie, 1997a, b; Robert & Bilderback, 1980).

Onwuegbuzie et al. (1997) defined statistics anxiety as an anxiety which occurswhen a student encounters statistics in any form and at any level. More specifically,Zeidner (1990) defined statistics anxiety more specifically as:

a performance characterized by extensive worry, intrusive thoughts, mentaldisorganization, tension, and physiological arousal when exposed tostatistics content, problems, instructional situations, or evaluative contexts,and is commonly claimed to debilitate performance in a wide variety ofacademic situations by interfering with the manipulation of statistics dataand solution of statistics problems. (p. 319)

Statistics anxiety typically comes to the fore during college, where students areassessed formally for their knowledge and understanding of statistics, as well as fortheir ability to apply statistical concepts to a wide variety of situations. However,because statistics is increasingly being introduced at secondary school, it is likely thatthe onset of this phenomenon typically occurs earlier than is currently assumed.Thus, researchers should study statistics anxiety among younger populations.

Antecedents of Statistics Anxiety

The antecedents of statistics anxiety can be categorised as situational, dispositionaland environmental. Situational antecedents refer to factors that surround the stimu-lus, whereas dispositional antecedents refer to factors which an individual brings tothe setting. Finally, environmental antecedents refer to events which occurred in thepast. Each of these classes of antecedents is discussed below.

Situational Antecedents of Statistics Anxiety

Situational antecedents include the following variables that have been found to berelated statistically significantly to statistics anxiety: statistics prior knowledge,statistics course grade, the status of the course (i.e. required or elective), major(statistics vs. non-statistics) attitudes towards calculators, course and instructorevaluation, and satisfaction with the statistics course (Morris et al., 1978; Sells,1978; Roberts & Saxe, 1982; Hunsley, 1987; Trimarco, 1997).

A number of mathematics-related variables has been found to prevail instatistics courses. In particular, researchers have documented an inverse relationshipbetween mathematics anxiety and statistics achievement (Bendig & Hughes, 1954;Fisch, 1971; Topf, 1976; Morris et al., 1978; Sells, 1978; Harvey et al., 1985;Hunsley, 1987). Similarly, Perney and Ravid (1990) contended that mathematics

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08

Statistics Anxiety 197

anxiety is transferred to statistics courses. Moreover, mathematics anxiety appears tobe a predictor of statistics anxiety (Onwuegbuzie et al., 1997). Notwithstanding, asnoted by Onwuegbuzie et al. (1997), statistics anxiety is distinct from mathematicsanxiety.

Other mathematics-based predictors of statistics anxiety include level of basicmathematics skills, number of prior mathematics courses completed, and poor priorachievement in mathematics (Tomazic & Katz, 1988; Zeidner, 1991; Wilson, 1997).However, most of these studies that identified mathematics-based antecedents werepublished prior to 1990before computer hardware in general and statisticalsoftware in particular became widely available, and before statistics instructors wereable to make their courses extremely applied by incorporating this technology. Theincreased use of computers in statistics courses likely has reduced the amount ofmathematical calculations students are expected to make. Thus, it is possible thatmathematics preparation and experience is not as important in contemporarystatistics courses. This should be the subject of future research. Researchers alsoshould investigate whether remedial courses, aimed at increasing mathematicalcompetence, help to reduce levels of statistics anxiety.

Finally, Wilensky (1997) contended that epistemological anxiety is a majorsource of statistics anxiety. Epistemological anxiety was defined as a feeling, oftenin the background, that one does not comprehend the meanings, purposes, sourcesor legitimacy of the mathematical objects one is manipulating and using (Wilensky,1997, p. 172).

Dispositional Antecedents of Statistics Anxiety

Zeidner (1991) and Benson (1989) found that perceived level of mathematicsself-concept and level of self-esteem are important contributors to statistics anxiety.Most recently, Onwuegbuzie (2000a) revealed that students with the lowest levels ofperceived scholastic competence, perceived intellectual ability and perceived creativ-ity tend to have the highest levels of statistics anxiety.

Another dispositional factor found to be related to statistics anxiety is perfec-tionism. Specifically, Onwuegbuzie and Daley (1999) reported that graduate stu-dents who hold unrealistic standards for significant others (i.e. other-orientatedperfectionists) and those who maintain a perceived need to attain standards andexpectations prescribed by significant others (i.e. socially-prescribed perfectionists)tend to have high levels of statistics anxiety. The role of perfectionism, however,should be explored further, especially in the area of applied statistics, where multipledata analysis procedures and interpretations stem from each data set. Indeed, manystudents mistakenly believe that, in analysing data, there is only one correct solution.Therefore, students with perfectionistic tendencies may be more anxious than theircounterparts when multiple solutions and interpretations exist.

Academic procrastination also has been linked to statistics anxiety (Onwueg-buzie, 2000b). However, the causal nature of this relationship is presently unknown.Similarly, levels of hope predict levels of statistics anxiety (Onwuegbuzie, 1998b).

Onwuegbuzie and Daley (1997) assessed the role of Gardners (1983) theory of

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


multiple intelligences in determining levels of statistics anxiety among public schoolteachers enrolled in a research methodology course. Findings revealed that teacherswho were less oriented towards linguistic and logical-mathematical intelligence andmore oriented towards spatial and interpersonal intelligence tended to have higherlevels of statistics anxiety. The finding pertaining to linguistic intelligence is particu-larly interesting. Bearing in mind the fact that statistics textbooks are considered bystudents to be extremely laconic and complex (Onwuegbuzie et al., 1997), it shouldnot be surprising that students who are not oriented towards linguistic intelligencetend to be the most statistics-anxious. Indeed, reading ability recently has beenlinked to achievement in quantitative-based research methodology courses (Collins& Onwuegbuzie, 2002).

Sutarso (1992) found significant relationships between students anxiety inlearning statistics and statistical preknowledge. Interestingly, Farbey and Roberts(1981) found a large increase in state anxiety between easy and difficult tasks whensolving statistical problems by hand. However, no difference in level of anxiety wasobserved between easy problems solved by hand and difficult problems solved withthe aid of the calculator. These researchers advocated the use of calculators forreducing levels of anxiety.

Onwuegbuzie and Daley (1996) conducted an experimental investigation exam-ining the contributions made by both examination-taking coping strategies andstudy coping strategies on the anxiety/performance relationship, under two types ofexamination conditions. Graduate students, who were enrolled in a statistics course,were assigned randomly to either an untimed or a timed examination condition.Both types of coping strategies made a significant contribution in explaining variancein test anxiety. Overall, students in the timed condition performed more poorly thandid students in the untimed condition. A significant interaction was found betweenexamination-taking coping strategies and examination condition: students with poorcoping strategies did not perform as well in the timed as in the untimed condition.No such interaction was found between study coping strategies and examinationcondition. According to Onwuegbuzie and Daley, these findings are consistent withan information processing interpretation, which suggests that different processesrelated to test anxiety affect statistics examination performance.

Environmental Antecedents of Statistics Anxiety

A few researchers have investigated gender differences in statistics anxiety.Specifically, females tend to report higher levels of statistics anxiety than do males(Benson, 1989; Benson & Bandalos, 1989; Bradley & Wygant, 1998). Also, olderstudents have been found to have the highest levels of statistics anxiety (Demaria-Mitton, 1987). Learning styles also have been implicated as representing an-tecedents of statistics anxiety (Onwuegbuzie, 1998c).

Racial differences also have been found with respect to statistics anxiety.Specifically, Onwuegbuzie (1999) noted that African-American graduate students ata university in the mid-southern United States reported higher levels of statisticsanxiety associated with worth of statistics, interpretation anxiety, and test and class

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


anxiety than did their Caucasian-American counterparts. These differences rangedfrom 0.45 to 0.56 standard deviations, suggesting moderate effect sizes. However, itis possible that the higher levels of statistics anxiety reported by African-Americanstudents represent a more generalised anxiety that came to the fore much earlier intheir school careers, resulting from relatively higher levels of underachievement.Thus, future research should compare ethnic and racial populations at differentpoints of the educational process, with respect to statistics anxiety and other formsof academic-related anxiety (e.g. test anxiety, mathematics anxiety).

Similarly, Bell (1998) found that international students reported statisticallysignificantly higher levels of statistics anxiety than did their non-international coun-terparts. However, extreme caution should be exercised in interpreting this findingbecause the number of international students in the study (n10) was very smalland no adjustment for Type I error was made, despite the fact that multiple tests ofsignificance were performed.

Effects of Statistics Anxiety

A growing body of research has documented a consistent negative relationshipbetween statistics anxiety and course performance (Zeidner, 1991; Elmore et al.,1993; Lalonde & Gardner 1993; Onwuegbuzie & Seaman 1995; Zanakis & Valenza1997). In fact, statistics anxiety has been found to be the best predictor of achieve-ment in research methodology (Onwuegbuzie et al., 2000) and statistics courses(Fitzgerald et al., 1996). Most recently, Onwuegbuzie (in press b), using pathanalytic techniques, found that statistics anxiety and expectation play a central rolein his Anxiety-Expectation Mediation (AEM) model, being related bi-directionallyto statistics achievement and, at the same time, moderating the relationship betweenstatistics achievement and research anxiety, study habits, course load, and thenumber of statistics courses taken. The AEM model is presented in Figure 1.Onwuegbuzie (in press b) posited that the pivotal role of statistics anxiety in theAEM model suggests that Wines (1980) Cognitive-Attentional-Interference theorycan be applied to the field of statistics, as it can be to the foreign language learningcontext. According to Onwuegbuzie, Wines theory predicts that anxiety interfereswith performance by impeding students ability to receive, to concentrate on, and toencode statistical terminology, language, formulae and concepts. Moreover, On-wuegbuzie theorised that anxiety reduces the efficiency with which memory pro-cesses are utilised while attempting to understand and to learn new statisticalmaterial, making it difficult to solve statistical problems.

Moreover, a causal link between statistics anxiety and course achievement hasbeen established. In particular, Onwuegbuzie and Seaman (1995) found that gradu-ate students with high levels of statistics test anxiety who were randomly assigned toa statistics examination that was administered under timed conditions tended tohave lower levels of performance than did their high-anxious counterparts who wereadministered the same test under untimed conditions. In a follow-up experimentalinvestigation among female college students, Onwuegbuzie (1995) reported asignificant interaction between statistics test anxiety and type of examination (i.e.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


FIG. 1. Final anxiety expectation mediation (AEM) model of statistics achievement showing allsignificant paths.

timed vs. untimed), with high-anxious female students showing a greater decrementin performance than did low-anxious female students in the untimed examinationcondition. Onwuegbuzie interpreted these results within conceptual frameworksdeveloped by Hill (1984) and Wine (1980), who suggested that differences betweenhigh- and low-anxious students in evaluative situations are due to differences inmotivational dispositions and attentional foci, respectively. Additionally, using qual-itative techniques, Onwuegbuzie (1997a) reported that statistics anxiety primarilyaffects a students ability fully to understand research articles, as well as to analyseand to interpret statistical data.

Thus, clearly, evidence has been documented that statistics anxiety is a debilita-tive phenomenon. However, it is possible that statistics anxiety also has a facilitativecomponent. For example, a certain amount of statistics anxiety may prevent stu-dents from being too complacent in preparing for an upcoming examination. Thus,future research should explore statistics anxiety as a facilitative construct, specifically

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


investigating at what point statistics anxiety may change from being facilitative todebilitative.

Multidimensionality of Statistics Anxiety

Statistics anxiety has been conceptualised as being multidimensional (Cruise &Wilkins, 1980; Cruise et al., 1985; Zeidner, 1991; Onwuegbuzie, 1997a; Onwueg-buzie et al., 1997). Zeidner (1991) reported that statistics anxiety comprised thefollowing two dimensions: statistics test anxiety and content anxiety. In an in-depthphenomenological study, Onwuegbuzie et al. (1997a) identified four general compo-nents of statistics anxiety, namely, instrument anxiety, content anxiety, interpersonalanxiety, and failure anxiety. Apparently, each of these components comprise severalsubcomponents. According to these authors, instrument anxiety consists of compu-tational self-concept and statistical computing anxiety. Content anxiety comprisesfear of statistical language, fear of application of statistics knowledge, perceivedusefulness of statistics and recall anxiety. Interpersonal anxiety is composed of fearof asking for help and fear of statistics instructors. Finally, failure anxiety consists ofstudy-related anxiety, test anxiety and grade anxiety.

Using factor analysis, Cruise et al. (1985) identified six components of statisticsanxiety, namely: worth of statistics, interpretation anxiety, test and class anxiety,computational self-concept, fear of asking for help and fear of statistics teachers.Additionally, Onwuegbuzie (1997a) reported that the following four dimensions ofstatistics anxiety are experienced by graduate students while they are engaged inwriting research proposals: perceived usefulness of statistics, fear of statisticallanguage, fear of application of statistics knowledge and interpersonal anxiety.

Using Cruise et al.s (1985) six-factor conceptualisation presented above, On-wuegbuzie (1998a) documented that test and class anxiety is the greatest source ofstatistics anxiety. Apparently, test and class anxiety had statistically significantlygreater endorsements than did the five other dimensions of statistics anxiety. Effectsizes associated with these differences, as measured by Cohens (1988) d, rangedfrom 0.62 to 0.90, suggesting large differences. Interpretation anxiety, which was thesecond most prevalent dimension, had statistically significantly higher mean ratingsthan did the four remaining dimensions. Thus, statistics instructors should becognisant of the fact that administering examinations and asking students to inter-pret statistical data induce the highest amount of anxiety.

Measures of Statistics Anxiety

Although several instruments have been developed to measure attitudes towardsstatistics (e.g. Roberts & Bilderbach, 1980; Wise, 1985; Schau & Stevens, 1995),few direct measures of statistics anxiety currently exist. Unfortunately, the vastmajority of research studies undertaken on statistics anxiety have used measures ofmathematics anxiety, in particular the MARS (Richardson & Suinn, 1972). Becausemathematics anxiety and statistics anxiety are related, but separate constructs, thevalidity of using measures of mathematics anxiety is in question.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


An extensive review of the literature revealed five scales that directly measurestatistics anxiety. These were the Statistics Anxiety Scale (SAS; Pretorius & Nor-man, 1992), the Multifactorial Scale of Attitudes Toward Statistics (MSATS;Auzmendi, 1991), the Statistics Anxiety Inventory (STAI; Zeidner, 1991), anunnamed instrument measure of statistics anxiety and attitudes developed byZanakis and Valenza (1997), and the Statistics Anxiety Rating Scale (STARS;Cruise et al., 1985).

The SAS (Pretorius & Norman, 1992) consists of one scale measuring GlobalStatistics Anxiety. Although the MSATS is designed to measure attitudes towardsstatistics, one of the five dimensions of this scale measures levels of statistics anxiety.Zeidners (1991) STAI is a 40-item instrument containing the following twosubscales; anxiety about statistics content and anxiety about statistics performanceand problem-solving capacity in evaluative situations. Zanakis and Valenzas (1997)36-item measure of statistics anxiety and attitudes contains the following six sub-scales:

student interest in and perceived worth of statistics; anxiety when seeking help for interpretation; computer usefulness and experience; math anxiety; understanding; test anxiety.

However, Zanakis and Valenzas (1997) scale does not appear to have been used inany other investigation. Finally, Cruise et al.s (1985) STARS presently is the mostutilised measure of statistics anxiety. As noted earlier, the STARS comprises sixcomponents of statistics anxiety, namely:

worth of statistics; interpretation anxiety; test and class anxiety; computational self-concept; fear of asking for help; fear of statistics teachers.

With the exception of the STARS, the aforementioned scales have not beensubjected to validity studies. Thus, information about the psychometric properties ofthese instruments is very limited. In order to advance the field of statistics anxiety,such validity studies must be undertaken. Furthermore, when using these instru-ments in studies, score reliability must be reported (Onwuegbuzie & Daniel, 2002).

The Treatment of Statistics Anxiety

Despite the prevalence of statistics anxiety, and the documented pervasive anddebilitative nature of this construct, it is surprising that only a few researchers haveinvestigated ways of reducing statistics anxiety. Specifically, Schacht and Stewart(1990) reported that students in statistics classes where humorous cartoon examples

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


were incorporated, perceived a reduction in their levels of mathematics anxiety. Forthese same students, a reduction in the actual levels of their mathematics anxietywas confirmed, although the exact causal nature of this reduction could not beestablished, because an experimental design was not employed. It is highly likely thatinterventions for different presentations of statistics anxiety may be different, de-pending on the manner in which it is manifested by each individual. For example,a student who has unpleasant physiological reactions in examination situations maybenefit from a different type of intervention to a student who has a negative view oftheir propensity or ability to succeed. The former may benefit from biofeedbacktraining, whereas the latter may benefit from some form of cognitive intervention.

In a follow-up article, Schacht and Stewart (1990) advocated teaching gim-micks in statistics classes. These gimmicks include using students as the source fromwhich data are collected and allowing students to create the statistical application.Sgoutas-Emch and Johnson (1998) and Onwuegbuzie et al. (1997) found journalwriting to be effective in reducing levels of anxiety, although the former authors didnot find a statistically significant decrease in anxiety levels. For statistics-anxiousfemales, Nielsen (1979) recommended that they be taught by female professors.

Dillon (1982) described a method used to reduce mathematics anxiety incollege-level statistics courses. Specifically, students share apprehension and anxietyabout statistics, and receive a lecture concerning ways of coping with their anxieties.At the end of the course, students again share their perceptions and feelings, andattempt to appreciate their increased mastery of statistical concepts.

Onwuegbuzie (2000c) found that examinations that are untimed and in whichsupporting material is allowed are regarded by the majority of students as inducingthe least amount of anxiety, as increasing levels of performance, and as promotinghigher-order thinking. In fact, students tend to rate performance assessments morehighly than other examination formats. Performance assessments involve providingstudents with projects, tasks, assignments or investigations, then evaluating theproducts that emerge in order to assess what students have learned and what theycan accomplish (Stenmark, 1991). As noted by educators and researchers alike (e.g.Worthen, 1993), performance assessment tasks should reflect essential, meaningfuland interesting performances that are linked to desired student outcomes that arerelevant to everyday life. That is, such methods of assessment should involveblending content with process and major concepts with specific problems (Baron,1990). To this end, performance assessments should evaluate what students can do,in addition to what they know (Hutchinson, 1995), being based on observing,documenting and analysing student work (Davey & Neill, 1991).

According to Elliott (1995), when using performance assessments, the perform-ance of students can be influenced positively by the following:

selecting assessment tasks that are aligned clearly and are connected to what hasbeen taught;

delineating clearly the scoring criteria for the assessment task to students priorto working on the task;

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


providing students with clear statements of standards and/or various models ofacceptable performance before they attempt a task;

encouraging students to undertake self-assessments of their performances; interpreting students performances by comparing them to those of other

students, as well as to standards that are developmentally appropriate.

Thus, where possible, statistics instructors should consider utilising performanceassessments. The use of other types of statistics assessments also should be exam-ined.

In a study of education and business students in graduate statistics courses,Wilson (1996) found that students deemed humor and testing procedures (such asopen book/open note testing) to be somewhat effective in reducing their anxietylevels, but that they were far more likely to attribute anxiety reduction to theteachers behaviour and personality. Especially effective was reassurance from theinstructor that the students could successfully complete the assigned tasks.

Wilson (1999a) employed a systematic programme of strategies purported inthe literature to reduce statistics anxiety: addressing the anxiety, using humour,applying statistics to real-world situations, reducing fear of evaluation and encourag-ing students to work in co-operative groups. She found that students perceived theinterpersonal style of the instructor as more important than specific strategies inreducing levels of anxiety. Addressing the anxiety actually increased some studentsdiscomfort, and working in cooperative groups was anxiety reducing only when teammembers were known and trusted to complete high quality work.

In a ranking of 16 anxiety-relieving factors mentioned by students in previousresearch by the author (i.e. Wilson, 1999b), students in a graduate educationalresearch course placed having open book/open note tests and working with a partnerin the computer lab at the top of the list. The instructors positive attitude,encouragement, and reassurance were ranked next, followed by humour and ad-dressing the anxiety. Scores for co-operative learning had the highest variability,showing that co-operative learning can both create and reduce anxiety, dependingon the composition of the team.

Another investigation of students in a graduate educational research course(Wilson, 2000) showed that, although instructors can do much to reduce levels ofstatistics anxiety, there is a certain amount of anxiety inherent in a class in whichstudents are asked to learn, and to respond to information and processes with whichthey are unfamiliar, including mathematical procedures, statistical concepts andresearch conventions. Outside factors, including family and job obligations andworkload in other courses, add to the stress that graduate students experience ineducational research classrooms.

Finally, and most recently, utilising Onwuegbuzies (1998b) finding of a rela-tionship between hope and statistics anxiety, Dilevko (2000) recommended thatresearch methodology and statistics class activities attempt to help students withunderstanding the course objectives, as well as being cognisant of the goals ofstatistics in order to control their own learning goals. According to Dilevko, statisticsanxiety can be reduced by improving students perceived worth of statistics and by

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


decreasing their fear of applying statistical knowledge and principals. Dilevkosuggested that a two-pronged approach be used to decrease statistics anxiety,namely:

using current news stories and similar sources to introduce and to explain basicstatistical concepts and methodological issues in research;

targeting their fear of application of statistics concepts by introducing studentsto older articles about subjects of interest, and asking them to read, to under-stand and to critique these articles, and to suggest how the research projectsdescribed in them could be modified, expanded and updated.

Dilevko contended that as a result of these two strategies, the importance of statisticsin everyday life is demonstrated through class discussion of interesting eventsreported in the popular press. Unfortunately, although appealing, Dilevko did notprovide any research evidence of the efficacy of his strategies.

Directions for Future Research in the Area of Statistics Anxiety

As documented above, recently, there has been an increase in the number ofresearchers investigating the construct of statistics anxiety. However, there is stillmuch that we do not know about this phenomenon. Moreover, much of the researchin this area has been undertaken among undergraduate students. Yet, as noted byOnwuegbuzie (1998a), statistics anxiety is extremely prevalent among graduatestudents, especially among women and minorities. Furthermore, because theses anddissertations typically necessitate the use of statistics, and because a significantproportion of students do not complete their theses and dissertations, and hencetheir graduate degree programs (Bowen & Rudenstine, 1992; Cesari, 1990), it ispossible that statistics anxiety, in part, may prevent some graduate students, es-pecially those who are most susceptible to anxiety, from completing their degreeprogrammes. As such, more investigations are needed among this often-neglectedpopulation, especially with respect to interventions.

REFERENCES

AUZMENDI, E. (1991) Factors Related to Attitudes Toward Statistics: a study with a Spanish sample,paper presented at the annual meeting of the American Educational Research Association,

Chicago, IL, April.BARON, J.B. (1990) How Science is Tested and Taught in Elementary School Science Classrooms: a

study of classroom observations and interviews, paper presented at the annual meeting of theAmerican Educational Research Association, Boston, MA, April.

BELL, J.A. (1998) International students have statistics anxiety too! Education 118, pp. 634636.BENDIG, A.W. & HUGHES, J.B. (1954) Student attitude and achievement in a course in introduc-

tory statistics, Journal of Educational Psychology, 45, pp. 268276.BENSON, J. (1989) Structural components of statistical test anxiety in adults: an exploratory

model, Journal of Experimental Education, 57, pp. 247261.BENSON, J. & BANDALOS, D. (1989) Structural model of statistical test anxiety, in: R. SCHWARZER,

H.M. VAN DER PLOEG & C.D. SPIELBERGER (Eds) Advances in Test Anxiety Research, Vol. 5,pp. 137154 (Hillsdale, NJ, Lawrence Erlbaum Associates).

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


BLALOCK, H.M. (1987) Some general goals in teaching statistics, Teaching Sociology, 15, pp.164172.

BOWEN, W.G. & RUDENSTINE, N.L. (1992) In pursuit of the PhD (Princeton, NJ, PrincetonUniversity Press).

BRADLEY, D.R. & WYGANT, C.R. (1998) Male and female differences in anxiety about statisticsare not reflected in performance, Psychological Reports, 82, pp. 245246.

CAINE, R.D., CENTA, D., DOROFF, C., HOROWITZ, J.H. & WISENBAKER, V. (1978) Statistics fromwho? Teaching Sociology, 6, pp. 3746.

CESARI, J.P. (1990) Thesis and dissertation support groups: a unique service for graduatestudents, Journal of College Student Development, 31, pp. 375376.

COHEN, J. (1988) Statistical Power Analysis for the Behavioral Sciences, 2nd edn. (New York, Wiley).COLLINS, K.M.T. & ONWUEGBUZIE, A.J. (2002) Relationship Between Reading Ability and Achieve-

ment in a Graduate-level Research Methodology Course, paper presented at the annual meetingof the American Educational Research Association, New Orleans, LA, April.

CRUISE, R.J., CASH, R.W. & BOLTON, D.L. (1985) Development and Validation of an Instrument toMeasure Statistical Anxiety, paper presented at the annual meeting of the Statistical Edu-cation Section, August, Proceedings of the American Statistical Association, Chicago, IL,pp. 9297.

CRUISE, R.J. & WILKINS, E.M. (1980) STARS: Statistical Anxiety Rating Scale, Unpublishedmanuscript, Andrews University, Berrien Springs, MI.

DAVEY, L. & NEILL, M. (1991) The Case Against a National Test, ERIC/TM Digest, ERICDocument Reproduction Service No. ED 338 703.

DEMARIA-MITTON, P.A. (1987) Locus-of-control, gender and type of major as correlates tostatistics anxiety in college students, Doctoral dissertation, American University 1987,Abstracts International, 48, p. 1397A.

DILEVKO, J. (2000) A new approach to teaching research methods courses in library and informationscience programs. Available at: http://www.alise.org/nondiscuss/conf00_%20DilevkoA%20New%20Approach.htm (accessed 30 October 2000).

DILLON, K.M. (1982) Statiscophobia, Teaching of Psychology, 9, p. 117.ELLIOTT, S.N. (1995) Creating Meaningful Performance Assessments, ERIC Digest E531, ERIC

Document Reproduction Service No. ED 381 985.ELMORE, P.B., LEWIS, E.L. & BAY, M.L.G. (1993) Statistics Achievement: a function of attitudes and

related experience, paper presented at the annual meeting of the American EducationalResearch Association, April, ERIC Document Reproduction Service No. 360 324.

FARBEY, L.J. & ROBERTS, D.M. (1981) Effects of Calculator Usage and Task Difficulty on StateAnxiety in Solving Statistical Problems, paper presented at the annual meeting of theAmerican Educational Research Association, Los Angeles, CA, April.

FISCH, R. (1971) Course evaluation, test anxiety, and final test results in a statistics course,Zeitschrift fur Entwicklung psychologie und padagogische Psychologie, 3, pp. 212228.

FITZGERALD, S.M., JURS, S. & HUDSON, L.M. (1996) A model predicting statistics achievementamong graduate students, College Student Journal, 30, pp. 361366.

GARDNER, H. (1983) Frames of Mind: the theory of multiple intelligences (New York, Basic Books).GAYDOSH, L.R. (1990) Syllabi and Instructional Materials for Social Statistics (Washington, DC,

American Sociological Association).HARVEY, A.L., PLAKE, B.S. & WISE, S.L. (1985) The Validity of Six Beliefs About Factors Related to

Statistics Achievement, paper presented at the annual meeting of the American EducationalResearch Association, Chicago, IL, April.

HILL, K.T. (1984) Debilitating motivation and testing: a major educational program, possiblesolutions, and policy applications, in: R.E. AMES & C. AMES (Eds) Research on motivation ineducation, Vol. 1, pp. 245274 (New York, Academic Press).

HUNSLEY, J.D. (1987) Cognitive processes in mathematics anxiety and test anxiety: the role ofappraisals, internal dialogue, and attributions, Journal of Educational Psychology, 79, pp.388392.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


HUTCHINSON, N.L. (1995) Performance Assessments of Career Development: ERIC Digest, ERICDocument Reproduction Service No. ED 414 518.

LALONDE, R.N. & GARDNER, R.C. (1993) Statistics as a second language? A model for predictingperformance in psychology students, Canadian Journal of Behavioral Science, 25, pp.108125.

LAZAR, A. (1990) Statistics courses in social work education, Journal of Teaching in Social Work,4, pp. 1730.

LUNDGREN, T.D. & FAWCETT, R. (1980) Statistics from statisticians, Teaching Sociology, 7, pp.191201.

MORRIS, L.W., KELLAWAY, D.S. & SMITH, D.H. (1978) Mathematics Anxiety Rating Scale:predicting anxiety experiences and academic performance in two groups of students, Journalof Educational Psychology, 70, pp. 589594.

NIELSEN, L. (1979) Feminism and factoral analyses: alleviating students statistics anxieties,College Student Journal, 13, pp. 5156.

ONWUEGBUZIE, A.J. (1995) Statistics test anxiety and women students, Psychology of WomenQuarterly, 19, pp. 413418.

ONWUEGBUZIE, A.J. (1997a) Writing a research proposal: the role of library anxiety, statisticsanxiety, and composition anxiety, Library and Information Science Research, 19, pp. 533.

ONWUEGBUZIE, A.J. (1997b) The teacher as researcher: the relationship between enrollment timeand achievement in a research methodology course, Reflection and Research, 3(1). Availableat: http://www.soe.gonzaga.edu/rr/v3n1/tony.html (accessed 30 October 2002).

ONWUEGBUZIE, A.J. (1998a) The dimensions of statistics anxiety: a comparison of prevalence ratesamong mid-southern university students, Louisiana Educational Research Journal, 23, pp.2340.

ONWUEGBUZIE, A.J. (1998b) The role of hope in predicting statistics anxiety. Psychological Reports,82, pp. 13151320.

ONWUEGBUZIE, A.J. (1998c) Statistics anxiety: a function of learning style? Research in the Schools,5, pp. 4352.

ONWUEGBUZIE, A.J. (1999) Statistics anxiety among African-American graduate students: anaffective filter? Journal of Black Psychology, 25, pp. 189209.

ONWUEGBUZIE, A.J. (2000a) Statistics anxiety and the role of self-perceptions, Journal of Educa-tional Research, 93, pp. 323335.

ONWUEGBUZIE, A.J. (2000b) Ill Begin my Statistics Assignment Tomorrow: the relationship betweenstatistics anxiety and academic procrastination, paper presented at the annual conference of theAmerican Educational Research Association (AERA), New Orleans, LA, April.

ONWUEGBUZIE, A.J. (2000c) Attitudes toward statistics assessments, Assessment and Evaluation inHigher Education, 25, pp. 325343.

ONWUEGBUZIE, A.J. (in press a) Prevalence of statistics anxiety among graduate students, Journalof Research in Education.

ONWUEGBUZIE, A.J. (in press b) Modeling statistics achievement among graduate students,Educational and Psychological Measurement.

ONWUEGBUZIE, A.J. & DALEY, C.E. (1996) The relative contributions of examination-takingcoping strategies and study coping strategies to test anxiety: a concurrent analysis, CognitiveTherapy and Research, 20, pp. 287303.

ONWUEGBUZIE, A.J. & DALEY, C.E. (1997) The role of multiple intelligences in statistics anxiety,Reflection and Research, 3(2). Available at: http://www.gonzaga.edu/rr/v3n2/onwueg-buzie.htm (accessed 30 October 2002).

ONWUEGBUZIE, A.J. & DALEY, C.E. (1999) Perfectionism and statistics anxiety, Personality andIndividual Differences, 26, pp. 10891102.

ONWUEGBUZIE, A.J. & DANIEL, L.G. (2002) A framework for reporting and interpreting internalconsistency reliability estimates, Measurement and Evaluation in Counseling and Development,35, pp. 89103.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


ONWUEGBUZIE, A.J. & SEAMAN, M. (1995) The effect of time and anxiety on statistics achieve-ment, Journal of Experimental Psychology, 63, pp. 115124.

ONWUEGBUZIE, A.J., DAROS, D. & RYAN, J. (1997) The components of statistics anxiety: aphenomenological study, Focus on Learning Problems in Mathematics, 19(4), pp. 1135.

ONWUEGBUZIE, A.J., SLATE, J., PATERSON, F., WATSON, M. & SCHWARTZ, R. (2000) Factorsassociated with underachievement in educational research courses, Research in the Schools,7, pp. 5365.

PERNEY, J. & RAVID, R. (1990) The Relationship Between Attitudes Toward Statistics, Math Self-con-cept, Test Anxiety and Graduate Students Achievement in an Introductory Statistics Course,paper presented at the annual meeting of the American Educational Research Association,Boston, MA, April, ERIC Document Reproduction Service No. ED 318607.

PRETORIUS, T.B. & NORMAN, A.M. (1992) Psychometric data on the statistics anxiety scale for asample of South African students, Educational and Psychological Measurement, 52, pp.933937.

RICHARDSON, F.C. & SUINN, R.M. (1972) The Mathematics Anxiety Rating Scale: psychometricdata, Journal of Counseling Psychology, 19, pp. 551554.

ROBERTS, D.M. & BILDERBACK, E.W. (1980) Reliability and validity of a statistics attitude survey,Educational and Psychological Measurement, 40, pp. 235238.

ROBERTS, D.M. & SAXE, J.E. (1982) Validity of a statistics attitude survey: a follow up study,Educational and Psychological Measurement, 42, pp. 907912.

SCHACHT, S. & STEWART, B.J. (1990) Whats funny about statistics? A technique for reducingstudent anxiety. Teaching Sociology, 18, pp. 5256.

SCHACHT, S. & STEWART, B.J. (1991) Whats funny about statistics? interactive/user-friendlygimmicks for teaching statistics, Teaching Sociology, 20, pp. 329332.

SCHAU, C. & STEVENS, J. (1995) The development and validation of the Survey of AttitudesToward Statistics, Educational and Psychological Measurement, 55, pp. 868875.

SELLS, L. (1978) Mathematicsa critical filter, Science Teacher, 45(2), pp. 2829.SGOUTAS-EMCH, S.A. & JOHNSON, C.J. (1998) Is journal writing an effective method of reducing

anxiety towards statistics? Journal of Instructional Psychology, 25, pp. 4957.STENMARK, J. (1991) Mathematics Assessment: myths, models, good questions, and practical suggestions

(Reston, VA, NCTM).SUTARSO, T. (1992) Some Variables in Relation to Students Anxiety in Learning Statistics, paper

presented at the annual meeting of the Mid-South Educational Research Association,Knoxville, TN, November.

TOMAZIC, T.J. & KATZ, B.M. (1988) Statistical Anxiety in Introductory Applied Statistics, paperpresented at the annual meeting of the American Statistical Association, New Orleans, LA,August.

TRIMARCO, K.A. (1997) The Effects of a Graduate Learning Experience on Anxiety, Achievement, andExpectations in Research and Statistics, paper presented at the annual meeting of theNortheastern Educational Research Association, Memphis, TN, October.

TOPF, M. (1976) In beginning research courses nursing students often display anxiety andnegative reactions. How many these be circumvented or corrected? Nursing Research, 25, p.439.

WILENSKY, U. (1997) What is normal anyway? Therapy for epistemological anxiety, TeachingSociology, 20(10), pp. 329332.

WILSON, V.A. (1996) Factors Related to Anxiety in Statistics, unpublished doctoral dissertation,University of Southern Mississippi, Hattiesburg.

WILSON, V. (1997) Factors Related to Anxiety in the Graduate Statistics Classroom, paper presentedat the annual meeting of the Mid-South Educational Research Association, Memphis, TN,November.

WILSON, V.A. (1999a) Student Response to a Systematic Program of Anxiety-reducing Strategies in aGraduate-level Introductory Educational Research Course, paper presented at the annualmeeting of the American Educational Research Association, Montreal, Que., April.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08


WILSON, V.A. (1999b) Reducing Statistics Anxiety: a ranking of sixteen specific strategies, paperpresented at the annual meeting of the Mid-South Educational Research Association, PointClear, AL, November.

WILSON, V.A. (2000) Stress and Stress Relief in the Educational Research Classroom, poster sessionpresented at the annual meeting of the American Educational Research Association, NewOrleans, LA, April.

WINE, J. (1980) Cognitive-attentional theory of test anxiety, in: I. G. SARASON (Ed.) Test Anxiety:theory, research and applications, pp. 349385 (Hillsdale, NJ, Lawrence Erlbaum Associates).

WISE, S.L. (1985) The development and validation of a scale measuring attitudes towardstatistics: an evaluation of multiple measures, Educational and Psychological Measurement, 48,pp. 513516.

WORTHEN, B.R. (1993) Critical issues that will determine the future of alternative assessment, PhiDelta Kappan, 74, pp. 444448.

ZANAKIS, S.H. & VALENZA, E.R. (1997) Student anxiety and attitudes in business statistics,Journal of Education for Business, 72(5), pp. 1016.

ZEIDNER, M. (1990) Does test anxiety bias scholastic aptitude test performance by gender andsociocultural group? Journal of Genetical Psychology, 150, pp. 175185.

ZEIDNER, M. (1991) Statistics and mathematics anxiety in social science studentssome interest-ing parallels, British Journal of Educational Psychology, 61, pp. 319328.

Dow

nloa

ded

By:

[The

Uni

vers

ity o

f Iow

a] A

t: 17

:21

7 Ja

nuar

y 20

08

statistics anxiety

Documents