Scott J. Seipel
Middle Tennessee State University
Charles H. Apigian
Middle Tennessee State University
Journal of Statistics Education Volume 13, Number 2 (2005), jse.amstat.org/v13n2/seipel.html
Copyright © 2005 by Scott J. Seipel and Charles H. Apigian, all rights reserved. This text may be freely shared among individuals, but it may not be republished in any medium without express written consent from the authors and advance notification of the editor.
Key Words:Business Statistics; Introductory Statistics Course; Perfectionism; Students.
Pacht (1984) noted that perfectionism is a prevalent characteristic in the general population. In an academic setting, perfectionism can lead to perceptions of a more difficult course, higher anxiety, and a more negative mood (Brown, Heimburg, Frost, Markis, Juster, and Leung 1999). Perfectionism is considered an aspect of personality (Habke and Flynn 2003), which is defined by Millon (1996) as “a complex pattern of deeply embedded psychological characteristics that largely nonconscious and not easily altered, expressing themselves automatically in almost every facet of functioning.” In comparison, attitudes are defined as the “tendency to evaluate objects favorably or unfavorably” (Olson and Maio 2003) and can be based on a set of beliefs. A favorable aspect of attitudes is that they are changeable (Petty, Wegener, and Fabrigar 1997). Perfectionism, as a dimension of personality, is more intractable. Thus, the study of perfectionism and its role in the statistics classroom may give instructors an insight into a relatively rigid personality trait that can cause significant student dissention and increased difficulty in the dissemination of knowledge.
The intent of this study is to focus the development of the statistics course on the internal needs of students. It is believed that a better understanding of the inherent behavioral weaknesses of students may lead to more common use of instructional modes designed to overcome these weaknesses. A psychological refinement of statistics instruction may result in increased student comprehension, academic achievement, and utilization of statistics post graduation. This is accomplished by (1) analyzing existing literature and validated measures of perfectionism, and then (2) developing a refined model of the perfectionist’s attributes and its relationship to performance in the classroom, by surveying statistics students. Finally, practical implications of the refined model are discussed and future directions for the statistics classroom are analyzed.
Much of the research involving perfectionism concerns the differentiation of positive and negative aspects of the trait. Hamachek (1978) identified individuals that set high standards and allow little leeway for mistakes as neurotic perfectionists, while those that set high standards and allow themselves some degree of latitude for not achieving those goals were labeled as normal perfectionists. Research by Enns and Cox (1999), Frost et al. (1993) and Hill, McIntire, and Bacharach (1997) isolated adaptive (healthy) and maladaptive (unhealthy) aspects of perfectionism, suggesting that some facets of perfectionism lead to higher performance and some lead to higher anxiety over performance. Frost et al. (1993) identified separate adaptive subscales in the HMPS and the MPS, specifically labeling subscales Personal Standards and Organization from the MPS as a “positive striving” characteristic of perfectionism. In the original research, Frost et al. (1990) also found that Personal Standards and Organization were negatively correlated with the frequency of procrastination, ascribing this to the possible planning of work strategies. Flett, Blankstein, Hewitt, and Koledin (1992) and Flett, Hewitt, and Martin (1995) determined that certain aspects of perfectionism can lead to the setting of unattainable goals and procrastination. The isolation of the impact of certain aspects of perfectionism was suggested by Frost et al. (1990), who noted that in order to understand perfectionism, it is necessary to examine its dimensions separately. The individual aspects of perfectionism as measured by the MPS have been validated by Frost et al. (1990) and Frost et al. (1997).
Given the nature of perfectionism and its bidirectional effects on performance, it is surprising that very little research has been done on the impact of perfectionism in the college classroom. One such study by Brown et al. (1999), involving female undergraduate students enrolled in an abnormal psychology course, found that the Personal Standards subscale of perfectionism was associated with improved academic performance on a subsequent exam when the individual scored higher than expected on an initial examination. Results of the study also indicated that, as a single dimension, Personal Standards was positively associated with overall academic performance as measured by GPA. Not unexpectedly, elevated levels of Personal Standards were linked with increased study time and time spent in discussion with instructors about grades. In a study of students enrolled in a second year psychology course, Bieling, Israeli, Smith, and Antony (2003) found that college students with higher levels of perfectionism set higher goals and were more likely to fall short. They also concluded that adaptive perfectionism was related modestly with performance and was positively associated with a preparedness attribute, which is consistent with the findings of Brown et al. (1999). It appears that in the limited research involving college students, Personal Standards has been identified as a clear link of perfectionism to academic performance. Therefore, the first research question to be examined in this article is:
RQ1: Will increased levels of Personal Standards (PS) be associated with increased levels of academic performance as measured by the overall grade in an introductory statistics classroom?
Aside from the PS subscale of perfectionism, the connection to academic performance is not as clear. Brown et al. (1999) did find that while higher levels of Concern over Mistakes were not predictive of lower performance, it did show higher anxiety and increased study habits, and perceptions of a more difficult course. Although Concern over Mistakes has been linked to anxiety over performance (Frost, Turcotte, Heimburg, Mattia, Holt, and Hope 1995), no direct link to performance was found in their study of undergraduate social science students. In fact, Frost et al.(1997) suggest that Concern over Mistakes plays no role in the frequency of mistakes. Thus, an additional research question to be examined in this article is:
RQ2: Will increased levels of Concern over Mistakes (CM) be associated with increased levels of academic performance as measured by the overall grade in an introductory statistics classroom?
There has been more success linking statistics anxiety among college students to perfectionism in the literature. Onwuegbuzie, DaRos, and Ryan (1997) stated that statistics anxiety “occurs as a result of encountering statistics in any form or at any level” and may "involve a complex array of emotional reactions which have the propensity to debilitate learning” (Onwuegbuzie and Daley 1999). Feinberg and Halperin (1978) and Onwuegbuzie and Seaman (1994) determined that many college students appear to have high levels of anxiety when confronted with the concepts, application, or education in statistics. Research by Onwuegbuzie and Daley (1999) on graduate liberal arts students in a research methodology course established that individuals who had an elevated level of Other-Oriented Perfectionism or Socially Prescribed Perfectionism tended to have high levels of statistics anxiety. When trait anxiety and procrastination are controlled, Self-Oriented Perfectionism was also found to be linked to statistics anxiety in a group of undergraduate social science students (Walsh and Ugumba-Agwunobi 2002). Statistics anxiety has been directly linked to academic performance in a graduate research methodology course (Onwuegbuzie 1997) and high school math matriculation scores (Zeidner 1991). However, this relationship has not been established in undergraduate students and the direct link between perfectionism and academic performance has not been investigated.
Perfectionism has been shown to exist in certain college populations. Onwuegbuzie and Daley (1999) found that graduate students in the social sciences exhibited extremely high levels of Self- and Other-Oriented Perfectionism. Walsh and Ugumba-Agwunobi (2002) determined that undergraduates in the same discipline displayed similarly high levels of Other-Oriented Perfectionism, lower levels of Self-Oriented Perfectionism, and higher levels of Socially Prescribed Perfectionism. The extent of perfectionism outside of these college populations has not been established. However, given that perfectionism has been linked to factors that can affect academic performance and that perfectionism is an innate and relatively unchangeable aspect of the personality of some students, it would appear beneficial to understand its direct implications on student performance and the effectiveness of the statistics instructor. Furthermore, little research has been put forward that addresses the psychological barriers preventing students from excelling in a standard business college statistics course, an arguably different type of student than those enrolled in the standard mathematics or social science statistics courses.
This research intends to investigate the relationship of perfectionism of college business statistics students and academic performance. As previous studies of perfectionism in college students were done on non-business students, the measures of perfectionism must be checked for reliability on this population. Additionally, the relationships of perfectionism subscales Personal Standards and Concern over Mistakes to academic performance as established in the literature need to be retested in the population of interest via the proposed research questions. While this research does not consider any other specific link between perfectionism and academic performance, it is proposed that additional links be investigated for possible insights that may lead to instructional improvement.
|Q1||My parents set very high standards for me.||PE||PEC||PPP|
|Q2||Organization is very important to me.||O||O||GAO|
|Q3||As a child, I was punished for doing things less than perfect.||PC||PEC||PPP||PPB|
|Q4||If I do not set the highest standards for myself, I am likely to end up
a second rate person.
|Q5||My parents never tried to understand my mistakes.||PC||PEC||PPP|
|Q6||It is important to me that I am thoroughly competent in everything I do.||PS||PS||GAO||PSB|
|Q7||I am a neat person.||O||O||GAO||OB|
|Q8||I try to be an organized person.||O||O||GAO|
|Q9||If I fail at work/school, I am a failure as a person.||CM||CMD||FM||CMB|
|Q10||I should be upset if I make a mistake.||CM||CMD||FM|
|Q11||My parents wanted me to do the best at everything.||PE||PEC||PPP|
|Q12||I set higher goals than most people.||PS||PS||GAO||PSB|
|Q13||If someone does a task at work/school better than I, then I feel like I failed|
the whole task.
|Q14||If I fail partly, it is as bad as being a complete failure.||CM||CMD||FM||CMB|
|Q15||Only outstanding performance is good enough in my family.||PE||PEC||PPP|
|Q16||I am very good at focusing my efforts on attaining a goal.||PS||PS||GAO|
|Q17||Even when I do something very carefully, I often feel that it is not quite right.||D||CMD||FM||DB|
|Q18||I hate being less than the best at things.||CM||CMD||FM|
|Q19||I have extremely high goals.||PS||PS||GAO||PSB|
|Q20||My parents have expected excellence from me.||PE||PEC||PPP||PPB|
|Q21||People will probably think less of me if I make a mistake.||CM||CMD||FM|
|Q22||I never felt like I could meet my parent’s expectations.||PC||PEC||PPP||PPB|
|Q23||If I do not do as well as other people, it means I am an inferior human being.||CM||CMD||FM||CMB|
|Q24||Other people seem to accept lower standards from themselves than I do.||PS||PS||FM||PSB|
|Q25||If I do not do well all the time, people will not respect me.||CM||CMD||FM|
|Q26||My parents have always had higher expectations for my future than I have.||PE||PEC||PPP||PPB|
|Q27||I try to be a neat (tidy) person.||O||O||GAO||OB|
|Q28||I usually have doubts about the simple everyday things I do.||D||CMD||FM||DB|
|Q29||Neatness is very important to me.||O||O||GAO||OB|
|Q30||I expect higher performance in my daily tasks than most people.||PS||PS||GAO||PSB|
|Q31||I am an organized person.||O||O||GAO||OB|
|Q32||I tend to get behind in my work because I repeat things over and over.||D||CMD||FM||DB|
|Q33||It takes me a long time to do something “right.”||D||CM||DFM|
|Q34||The fewer mistakes I make, the more people will like me.||CM||CMD||FM||CMB|
|Q35||I never felt like I could meet my parent’s standards.||PC||PEC||PPP||PPB|
Note. CM = Concern over Mistakes; D = Doubts about Actions; PE = Parental Expectations; PC = Parental Criticism; PS = Personal Standards; O = Organization; CMD = Concern over Mistakes and Doubts; PEC = Parental Expectations and Criticism; FM = Fear of Mistakes; GAO = Goal/Achievement Orientation; PPP = Perceived Parental Pressure; PPB = Parental Perceptions. “B” Subscript indicates brief version of subscale.
Subsequent studies have challenged the number of subscales in the MPS and the arrangement of the items to subscales. Stöber (1998) argued for the existence of four rather than six perfectionism subscales stemming from the original Frost MPS instrument (Table 1). In the model proposed by Stöber, Concern over Mistakes and Doubts about Actions from the Frost MPS model were combined into a single factor named Concern over Mistakes and Doubts (CMD). In a similar manner, subscales Parental Expectations and Parental Criticism were aggregated into a factor named Parental Expectations and Criticism (PEC). All items as specified in the original Frost MPS instrument were retained without change and items preserved their allocation to subscales in their original or aggregate form. An apparent lack of unidimensionality within the subscales was noted - Stöber (1998) identified several items that had significant secondary loadings. This reorganization of the Frost MPS model will be referred to as the MPS-4 in this paper to signify the employment of four subscales. This arrangement was confirmed in a later paper by Stumpf and Parker (2000).
A three-factor solution was also proposed as providing a better fit than the original six-factor model suggested by Frost et al. (1990). Purdon, Antony, and Swinson (1999) identified three factors - Fear of Mistakes (FM), Goal/Achievement Orientation (GAO), and Perceived Parental Pressure (PPP) - which were created through the combination of original subscales and the reallocations of items attributed to Personal Standards (Table 1). FM consisted of items previously attributed by Frost et al. (1990) to Concern over Mistakes and Doubts about Actions and included some of the items ascribed to the Personal Standards subscale. Subscale GAO included the balance of the Personal Standards items along with items from the Organization subscale. Identical to the Parental Expectations and Criticism (PEC) subscale suggested by Stöber (1998), PPP was made up of all items attributed to Parental Expectations and Parental Criticism. MPS-3 will be used as the moniker for the three-factor perfectionism model in this paper.
Cox et al. (2002) conducted an extensive confirmatory analysis of the various perfectionism models in order to elucidate the factorial nature of the Frost MPS. Although the original six-factor solution was preferable to the three- and four-factor solutions, it too failed to meet any of the evaluative criteria used in their study. In an effort to provide a more reliable model, Cox et al. (2002) used exploratory factor analysis to cull a set of items that best represented each of the factors. These derived factors were then cross-validated with a confirmatory factor analysis (CFA) on a second dataset. Unidimensionality of the subscales was improved by eliminating items that cross-loaded on more than one factor. Their five-factor solution (Table 1) included only 22 of the original 35 items that comprised the Frost MPS. This brief version of the MPS, referred to as MPS-B in this article, defined each of the original subscales from the Frost MPS with a smaller set of items. Subscales Parental Expectations and Parental Criticism were combined and summarized by a new brief subscale called Parental Perceptions (PPB). Acronyms for brief versions of the original subscales, as determined by Cox et al. (2002), are notated by the subscript “B” in this paper to distinguish them from the original subscales defined in the MPS.
The measure of performance in a statistics course provided a more difficult problem. Although the same textbook and general class structure was used, the two instructors utilized dissimilar assignment/project/exam configurations, graded student submissions differently, and used different scaling for the assignment of grades. To allow for more consistent results across instructors, it was determined that the final percentage of available points would be used as the measure of student performance. It is acknowledged that student grades may not often accurately reflect statistical learning, but it is clear that grades are the most commonly accepted measure of performance in academia.
Note that the use of a single measure for academic performance will have specific effects on the nature of the structural model formed. A direct result of this approach is the elimination of measurement error as it pertains to the measure of academic performance. The general effect is that of a standard regression analysis, where the dependent variable is assumed to be measured without error.
For additional information on the use of structural equation modeling, Hoyle (1995) provides a thorough discussion of the issues, testing, and application of this statistical technique. Further information can be attained from the website for the LISREL software: www.ssicentral.com/lisrel/mainlis.htm.
|Model||n||df||/df||TLI||CFI||SRMR||RMSEA||90% CI RMSEA|
P-values are in parentheses
CMB = brief Concern over Mistakes; DB = brief Doubts about Actions; PPB = brief Parental Perceptions;
PSB = brief Personal Standards; OB = brief Organization.
|Model||df||/df||TLI||CFI||SRMR||RMSEA||90% CI RMSEA|
|Measurement Model||353.34||216||1.64||0.93||0.94||0.076||0.055||0.045, 0.066|
|SEM of MPS-B to Grade||354.52||216||1.64||0.92||0.94||0.077||0.056||0.046, 0.067|
|SEM of PS and O to Grade||61.87||33||1.87||0.96||0.97||0.057||0.066||0.040, 0.091|
Figure 1. Overall MPS-B model of the factor structures of perfectionism and academic performance, and their relationship.
Based on an acceptable measurement model, an initial structural equation was modeled allowing relationships between all five MPS-B subscales and the measure of academic performance (Figure 1). Note that rectangles represent observed variables in the study, and ellipses represent latent variables. Latent variables are unobserved variables, factors, or constructs that are assumed to be measured by one or more directly observable variables. Measurement error, in terms of adequacy in describing the latent variables, is signified by the arrows leading into the observed variables. Single-arrowed lines represent path coefficients in the model, whereas double-arrowed lines between the ellipses indicate correlations between these unobserved variables. Path coefficients are the estimated effect size and can be interpreted similarly to regression weights. The metric for the coefficient will be the scale of the originating variable if observed and in terms of standard deviations if the originating variable is latent. Note that structural equation models do not utilize intercept terms.
As indicated in Table 6, fit statistics showed an acceptable fit of this structural model with all statistics within criteria bounds. A statistically significant positive relationship was found between Personal Standards and academic performance (p = 0.011), addressing the question raised by RQ1. An additional non-theorized negative relationship between Organization and academic performance (p = 0.010) was also found. No other perfectionism subscale was found to have a significant relationship with academic performance - observed significance levels for the relationships between Concern over Mistakes, Doubts about Actions, and Parental Perceptions with academic performance were 0.826, 0.418, and 0.097 respectively. Thus, there was insufficient evidence of a relationship between Concern over Mistakes and academic performance (RQ2), consistent with prior studies in other academic fields.
To determine the strength and significance of the primary relationships between perfectionism and the measure of academic performance, subscales not showing a significant relationship in the initial model were dropped. Model fit indices for this reduced model showed acceptable model fit (Table 6). The significance and the magnitude of the relationships of Personal Standards and Organization to academic performance were not materially changed in this model (Figure 2).
Figure 2. Final model of the factor structures of perfectionism and academic performance, and their relationship.
Of particular interest from these results were the nature and the direction of the relationship found between Personal Standards, Organization, and the measure of academic performance. As predicted by previous studies, Personal Standards showed a positive relationship with performance, with a standardized coefficient of 0.19. The relationship of perfectionism subscale Organization to performance was negative, with a standardized coefficient of -0.20. However, consistent with the correlations found in the CFA on the MPS-B scale, the correlation of Personal Standards and Organization remained positive (r = 0.24, p = 0.001). Personal Standards and Organization have been segregated from the other subscales and labeled as adaptive aspects of perfectionism (Frost et al., 1993). The positive correlation between these subscales is expected, as is the positive coefficient of Personal Standards and academic performance. The suggestion from the results that Organization, a positive aspect of perfectionism, has a negative relationship with academic performance is disconcerting. This result was also particularly interesting in that although the relationships of Personal Standards and Organization to academic performance were in opposing directions, the relationship between the two perfectionism subscales remained positive. To determine if the relationship of Organization to academic performance was invariant to instructor, semester (fall and summer), and gender, tests were performed using the final model (Figure 2). No significant difference was found between instructors ( = 2.27, df = 1, p = 0.132), semesters ( = 1.02, df = 1, p = 0.313), or genders ( = 0.27, df = 1, p = 0.603).
The main purpose of this study was to determine whether perfectionism may be related to the ability of a student to achieve success in a statistics classroom. Central to that purpose were two primary research questions assessing the relationship between perfectionism subscales Personal Standards and Concern over Mistakes with academic achievement. Regarding Personal Standards, which was theorized as having a direct positive effect on academic performance in the statistics classroom, the results were supportive. This result is in agreement with research done in other academic fields and should be received positively by instructors in this curriculum. Personal Standards is defined by Frost et al. (1990) as a person’s tendency to set “very high standards” and reflects “excessive importance placed on these high standards for self-evaluation.” The connection between this adaptive aspect of perfectionism and academic performance seems to validate the belief that statistics is not unique among college subjects in that hard work and high standards will result in increased achievement.
The confirmation that the factor Concern over Mistakes is not related to academic achievement is also of some importance. Concern over Mistakes is considered a maladaptive aspect of perfectionism that is defined by Frost et al. (1990) as “negative reactions to mistakes, a tendency to interpret mistakes as equivalent to failure, and a tendency to believe that one will lose the respect of others following failure.” Although students often consider the field of statistics as mathematics, statisticians realize that there is usually more than one way to analyze and interpret data. It would have been a concern to instructors if excessive apprehension by students over potentially subjective decisions was detrimental to academic achievement. Fortunately, that is not the case.
The investigation of the relationship between other factors of perfectionism and academic performance generally agreed with the existing literature, with Organization being the lone exception. Outside of that exception, there is no clear indication from this research that student perfectionism is linked in ways to academic performance in a statistics course that are not in line with other disciplines. The relationship of Organization to academic performance appears unique in the literature. This result is both surprising and intriguing, since Organization and Personal Standards are both considered adaptive aspects of perfectionism. The finding that Organization is working against academic achievement is contrary to expectations. It is possible that this relationship is the result of a Type I error. Although all items on the MPS and its derivatives loaded properly on their respective factors and correlations between factors agreed with previous research, the shear number of required estimations would naturally elevate the probability of a Type I error. In terms of coefficient estimation, five new relationships were estimated between perfectionism subscales and academic performance in the original structural model. Given the chance that the result was not generated erroneously, it may be beneficial to understand the nature of the Organization subscale and the role it might play in academic achievement in the statistics classroom.
As an aspect of perfectionism, Frost et al. (1990) stated that the dimension, Organization, overemphasizes “precision, order, and organization.” Hollender (1965) defined it as a tendency to be “fussy and exacting” going so far as to state that these individuals think “there is a place for everything, and everything must be in its place.” However, Organization is considered the least interlinked of the subscales of perfectionism, but yet it regularly shows the highest level of reliability (Frost et al., 1990).
One possible explanation of the relationship between Organization and academic performance would be through statistics anxiety. Research by Onwuegbuzie and Daley (1999) has linked statistics anxiety to Socially Prescribed and Other-Oriented perfectionism, factors found in the Hewitt et al. (1991) multidimensional perfectionism scale (HMPS). Subscales from the HMPS has been linked to subscales from the Frost MPS by Frost et al. (1993). If statistics anxiety explained much of the negative relationship between Organization and academic performance, it would be expected that HMPS subscales Socially Prescribed and Other-Oriented perfectionism would be significantly correlated to the Personal Standards and Organization subscales from the Frost MPS. The linkages found by Frost et al. (1993) show that this is not that case. Personal Standards and Organization correlate highly with Self-Oriented perfectionism. However, in a subsequent paper, Walsh and Ugumba-Agwunobi (2002) found that Self-Oriented perfectionism was related to a fear of statistics instructors and Computational Self-Concept when procrastination and trait anxiety are controlled. Cruise, Cash, and Bolton (1985) define Computational Self-Concept, a dimension of statistics anxiety, as the self perception of mathematical abilities and the anxiety experienced when attempting to solve mathematical problems. Walsh and Ugumba-Agwunobi (2002) attributed the link between Self-Oriented perfectionism and Computational Self-Concept to a student’s history with statistics courses and their inability to meet their own high expectations in those courses. As Personal Standards was defined by Frost et al. (1990) as the tendency to set “very high standards and the excessive importance placed on these high standards for self-evaluation”, the link of Computation Self-Concept to subscales from Frost’s MPS would seemingly be to Personal Standards. There has been no link proposed in the literature of statistics anxiety to Organization.
For benefits to be gleaned from this study, the practical implications must be addressed. Design considerations may need to be made in future textbooks to allow for the processing of statistical ideas without the mathematical rigor imposed in the past. With the additional emphasis now placed on the use of statistical software, statistics courses are shifting their focus from mathematical explanation to business analysis and decision making. This may make it even more imperative that business statistics instructors take the necessary time to link topics conceptually. A clear “final destination” to the knowledge gained during the semester should be shown with an explanation of how each subject relates to that “final destination”. Overviews of where and how statistical techniques fit together and aid in the analysis and interpretation of data should be considered to improve the organization of the material. Instructors may also need to place additional importance on the relationship of statistical techniques to each other and how the use of multiple techniques may work collectively to answer questions not addressable by a single approach. However, this cannot be achieved without placing sufficient emphasis on the structure underlying statistics. Common ground must be found to allow for student perception of a coherent and meaningful linkage between statistical topics when the mathematical connection is minimized.
A promising teaching technique that may alleviate some of the organizational issues is the implementation of a constructivist approach, whereby students actively construct their knowledge through activation of previously learned material. Verkoeijen et al. (2002) describe the constructivist approach as a process where new information is linked to preexisting knowledge structures leading “to the development of sophisticated and elaborate mental knowledge structures”. For this to work in the statistics classroom, instructors should be able to link current topics with other business-related material that will help the students comprehend more than just the process, but the reason for its use. For example, the instruction of hypothesis testing may not connect with students unless they understand the reason for performing such a test and the impact it may have on everyday business decision making.
Albert, J. (2000), “Using a Sample Survey Project to Assess the Teaching of Statistical Inference,” Journal of Statistics Education [Online], 8(1). jse.amstat.org/secure/v8n1/albert.cfm
Anderson, J. C., and Gerbing. D. W. (1988), “Structural Equation Modeling in Practice: A review and recommended two-step approach,” Psychological Bulletin, 103, 411-423.
Bentler, P. M. (1990), “Comparative Fit Indexes in Structural Modeling,” Psychological Bulletin, 107, 238-246.
Bentler, P. M. and Bonnet, D. G. (1980), “Significance Tests and Goodness of Fit in the Analysis of Covariance Structures,” Psychological Bulletin, 88, 588-606.
Bieling, P. J., Israeli, A., Smith, J., and Antony, M. M. (2003), “Making the Grade: the behavioural consequences of perfectionism in the classroom,” Personality and Individual Differences, 35, 163-178.
Bordley, R. F. (2001), “Teaching Decision Theory in Applied Statistics Courses,” Journal of Statistics Education [Online], 9(2). jse.amstat.org/v9n2/bordley.html
Brown, E. J., Heimburg, R. G., Frost, R. O., Makris, G. S., Juster, H. R., and Leung, A. W. (1999), “Relationship of Perfectionism to Affect, Expectations, Attributions and Performance in the Classroom,” Journal of Clinical Psychology, 18, 98-120.
Browne, M. W., and Cudeck, R. (1993), “Alternative Ways of Assessing Model Fit.” In K.A. Bollen and J.S. Long (Eds.), Testing Structural Models (pp. 136-162). Newbury Park, CA: Sage Publications, Inc.
Cox, B. J., Enns, M. W., and Clara, I. P. (2002), “The Multidimensional Structure of Perfectionism in Clinically Distressed and College Student Samples,” Psychological Assessment, 14, 365-373.
Cruise, R. J., Cash, R. W., and Bolton, D. L. (1985), “Development and Validation of an Instrument to Measure Statistical Anxiety,” 1985 Proceedings of the American Statistical Association, Statistics Education Section (pp. 92-97). Alexandria, VA: American Statistical Association.
Dauphinee, T. L., Schau, C., and Stevens, J. J. (1997), “Survey of Attitudes Towards Statistics: Factor structure and factorial invariance for females and males,” Structural Equation Modeling, 4, 129-141.
Enns, M. W., and Cox, B. J. (1999), “Perfectionism and Depression Symptom Severity in Major Depressive Disorder,” Behavior Research and Therapy, 37, 783-794.
Enns, M.W., and Cox, B.J. (2002), “The Nature and Assessment of Perfectionism: A critical analysis.” In G.L. Flett and P.L. Hewitt (Eds.), Perfectionism: Theory, research, and treatment (pp. 33-62). Washington, DC: American Psychological Association.
Feinberg, L, and Halperin, S. (1978), “Affective and Cognitive Correlates of Course Performance in Introductory Statistics,” Journal of Experimental Education, 46(4), 11-18.
Flett, G., Blankstein, R., Hewitt, P., and Koledin, S. (1992), “Components of Perfectionism and Procrastination in College Students,” Social Behaviour and Personality, 6, 147-160.
Flett, G., Hewitt, P., and Martin, T. (1995), “Dimensions of Perfectionism and Procrastination.” In S. Ferrari, J. Johnson, and W. McCown (Eds.), Procrastination and Task Avoidance: Theory, research, and treatment (pp. 113-136). London: Plenum Press.
Frost, R. O., Heimburg, R. G., Holt, C. S., Mattia, J. I., and Neubauer, A. L. (1993), “A Comparison of Two Measures of Perfectionism,” Personality and Individual Differences, 14, 119-126.
Frost, R. O., Marten, P., Lahart, C., and Rosenblate, R. (1990), “The Dimensions of Perfectionism,” Cognitive Therapy and Research, 14, 449-468.
Frost, R. O., Trepanier, K. L., Brown, E. J., , Heimburg, R. G., Juster, H. R., Leung, A. W., and Makris, G. S. (1997), “Self-Monitoring of Mistakes Among Subjects High and Low in Concern Over Mistakes,” Cognitive Therapy and Research, 21, 209-222.
Frost, R. O., Turcotte, T. A., Heimburg, R. G., Mattia, J. I., Holt, C. S., and Hope, D. A. (1995), “Reactions to Mistakes Among Participants High and Low in Perfectionistic Concern Over Mistakes,” Cognitive Therapy and Research, 19, 195-205.
Gal, I., and Ginsburg, L. (1994), “The Role of Beliefs and Attitudes in Learning Statistics: Towards an assessment framework,” Journal of Statistics Education [Online], 2(2). jse.amstat.org/v2n2/gal.html
Gal, I., Ginsburg, L., and Schau, C. (1997), “Monitoring Attitudes and Beliefs in Statistics Education.” In I. Gal and J.B. Garfield (Eds.), The Assessment Challenge in Statistics Education (pp. 37-51). Netherlands: IOS Press.
Habke, A. M., and Flynn, C. A. (2003), “Interpersonal Aspects of Trait Perfectionism.” In G.L. Flett and P.L. Hewitt (Eds.), Perfectionism: Theory, Research and Treatment (pp. 151-180). Washington, D.C.: American Psychological Association.
Hamachek, D. E. (1978), “Psychodynamics of Normal and Neurotic Perfectionism,” Psychology, 15, 27-33.
Hewitt, P. L., and Flett, G. L. (1991), “Perfectionism in the Self and Social Contexts: Conceptualization, assessment, and association with psychopathology,” Journal of Personality and Social Psychology, 60, 456-470.
Hill, R.W., McIntire, K., and Bacharach, V. R. (1997), “Perfectionism and the Big Five Factors,” Social Behaviour and Personality, 12, 257-270.
Hollender, M. H. (1965), “Perfectionism,” Comprehensive Psychiatry, 6, 94-103.
Hoyle, R. H. (Ed.) (1995), Structural Equation Modeling: Concepts, Issues, and Applications, Thousands Oaks, CA: Sage.
Hu, L., and Bentler, P. M. (1999), “Cutoff Criteria for Fit Indexes in Covariance Structure Analysis: Conventional criteria versus new alternatives,” Structural Equation Modeling, 6, 1-55.
Jöreskog, K. G. (1971), “Statistical Analysis of Sets of Congeneric Tests,” Psychometrika, 36, 109-33.
Kline, R. B. (1998), The Principles and Practice of Structural Equation Modeling, New York: Guilford Press.
MacCallum, R. (1986), “Specification Searches in Covariance Structure Modeling,” Psychological Bulletin, 100, 107-120.
MacCallum, R .C., Browne, M. W. and Sugwara, H. M. (1996), “Power Analysis and Determination of Sample Size for Covariance Structure Modeling,” Psychological Methods, 1, 130-149.
Magel, R. C. (1998), “Using Cooperative Learning in a Large Introductory Statistics Class,” Journal of Statistics Education [Online], 6(3). jse.amstat.org/v6n2/magel.html
Marasinghe, M. G., Meeker, W. Q., Cook, D., and Shin, T. (1996), “Using Graphics and Simulation to Teach Statistical Concepts,” The American Statistician, 50, 342-351.
Millon, T. (with Davis, R. D.) (1996), Disorders of Personality: DSM-IV and Beyond (2nd ed.), New York: Wiley.
Mills, J. D. (2002), “Using Computer Simulation Methods to Teach Statistics: A review of the literature,” Journal of Statistics Education [Online], 10(1). jse.amstat.org/v10n1/mills.html
Olson, J. M. and Maio, G. R. (2003), “Attitudes in Social Behavior.” In I.B. Weiner, T. Millon, and M.J. Lerner (Eds.), Handbook of Psychology: Personality and Social Psychology (pp. 299-325). Hoboken, NJ: John Wiley.
Onwuegbuzie, A. J. (1997), “Writing a Research Proposal: The Role of library anxiety, statistics anxiety and composition anxiety,” Library and Information Science Research, 19, 5-33.
Onwuegbuzie, A. J., and Daley, C. E. (1999), “Perfectionism and Statistics Anxiety,” Personality and Individual Differences, 26, 1089-1102.
Onwuegbuzie, A. J., DaRos, D., and Ryan, J. (1997), “The Components of Statistics Anxiety: A phenomenological study,” Focus on Learning Problems in Mathematics, 19(4), 11-35.
Onwuegbuzie, A. J., and Seaman, M. (1994), “The Effect of Time and Anxiety on Statistics Achievement,” Journal of Experimental Psychology, 63, 115-124.
Pacht, A. R. (1984), “Reflections on Perfection,” American Psychologist, 39, 386-390.
Petty, R. E., Wegener, D. T., and Fabrigar, L. R. (1997), “Attitudes and Attitude Change,” Annual Review of Psychology, 48, 609-647.
Purdon, C., Antony, M. M., and Swinson, R. P. (1999), “Psychometric Properties of the Frost Multidimensional Perfectionism Scale in a Clinical Anxiety Disorders Sample,” Journal of Clinical Psychology, 55, 1271-1286.
Reid, A., and Petocz, P. (2002), “Students’ Conceptions of Statistics: A phenomenographic study,” Journal of Statistics Education [Online], 10(2). jse.amstat.org/v10n2/reid.html
Rinaman, W. C. (1998), “Revising a Basic Statistics Course,” Journal of Statistics Education [Online], 6(2). jse.amstat.org/v6n2/rinaman.html
Roberts, D. M., and Bilderback, E. W. (1980), “Reliability and Validity of a Stataistics Attitude Survey,” Education and Psychological Measurement, 40, 235-238.
Roberts, D. M., and Saxe, J. (1982), “Validity of a Statistics Attitude Survey: a follow-up study,” Educational and Psychological Measurement, 42, 907-912.
Schau, C., Stevens, J., Dauphinee, T. L., and Del Vecchio, A. (1995), “The Development and Validation of the Survey of Attitudes Toward Statistics,” Educational and Psychological Measurement, 55, 868-875.
Sedlmeier, P. (1999), Improving Statistical Reasoning: Theoretical Models and Practical Implication, Mahwah, NJ: Lawrence Erlbaum.
Smith, G. (1998), “Learning Statistics by Doing Statistics,” Journal of Statistics Education [Online], 6(3). jse.amstat.org/v6n3/smith.html
Steiger, J. H. (1990), “Structural Model Evaluation and Modifications: An interval estimation approach,” Multivariate Behavioral Research, 25, 173-180.
Stöber, J. (1998), “The Frost Multidimensional Perfectionism Scale Revisited: More perfect with four (instead of six) dimensions,” Personality and Individual Differences, 24, 481-491.
Stumpf, H. and Parker, W. D. (2000), “A Hierarchical Structure Analysis of Perfectionism and its Relation to Other Personality Characteristics,” Personality and Individual Differences, 28, 837-852.
Tucker, C., and Lewis, C. (1973), “A Reliability Coefficient for Maximum Likelihood Factor Analysis,” Psychometrika, 38, 1-10.
Velleman, P. F. and Moore, D. S. (1996), “Multimedia for Teaching Statistics: Promises and pitfalls,” American Statistician, 50, 217-225.
Verkoeijen, P. P. J. L., Imbos, Tj., van de Wiel, M. W. J., Berger, M. P. F., and Schmidt, H. G. (2002), “Assessing Knowledge Structures in a Constructive Learning Environment,” Journal of Statistics Education [Online], 10(2). jse.amstat.org/v10n2/verkoeijen.html
Walsh, J. J., and Ugumba-Agwunobi, G. (2002), “Individual Differences in Statistics Anxiety: The roles of perfectionism, procrastination and trait anxiety,” Personality and Individual Differences, 33, 239-251.
Wise, S. L. (1985), “The Development and Validation of a Scale Measuring Attitudes Toward Statistics,” Educational and Psychological Measurement, 45, 401-405.
Yesilcay, Y. (2000), “Research Project in Statistics: Implications of a case study for the undergraduate statistics curriculum,” Journal of Statistics Education [Online], 8(2). jse.amstat.org/secure/v8n2/yesilcay.cfm
Zeidner, M. (1991), “Statistics and Mathematics Anxiety in Social Science Students: Some interesting pitfalls,” British Journal of Educational Psychology, 61, 319-328.
Scott J. Seipel
Department of Computer Information Systems
Middle Tennesee State University
Murfreesboro, TN 37132
Charles H. Apigian
Department of Computer Information Systems
Middle Tennessee State University
Murfreesboro, TN 37132
Volume 13 (2005) | Archive | Index | Data Archive | Information Service | Editorial Board | Guidelines for Authors | Guidelines for Data Contributors | Home Page | Contact JSE | ASA Publications