Arab and Malay Students’ Attitudes toward Statistics and Their Learning Styles: A Rasch Measurement Approach

Students’ learning of statistics has been studied from a variety of angles, and this study is no different. The main purpose is to compare the Malay and Arab students’ attitudes toward learning statistics and their learning styles in understanding statistics. A survey questionnaire and face-to-face interview techniques were used to elicit information from 150 students based on the cohort. They were asked about how they learn to solve statistical problems based on Kolb’s four learning cycles: feeling, reflective observation, thinking, and doing. Attitude responses were numerically recorded based on a five-point Likert scale, while preference for learning styles was recorded as 1 (Do and Feel) or 0 (Watch and Think). Both attitude and learning style data were combined and subjected to Rasch analysis. Results show that a majority of the Arab and Malay students have moderate to high positive attitude toward learning statistics. Generally, students from both cultures are classified as the “Accommodating” type with a preference for doing and feeling from the experience of doing statistical problems. Arab students are classified as the “Assimilating” type with a preference for thinking, reflecting, and learning from observation, while Malay students are classified as the “Converging” type with a preference for thinking and doing statistical exercises.

Attitudes toward Statistics and Statistical Literacy of Public Senior High School Students

Statistics has proven its usefulness in research over centuries to produce quality insights and data-driven decision-making. Learning statistics not only rely on cognitive but other factors such including attitude as well. This descriptive-correlational research determined the attitudes toward statistics in the components of affect, cognitive competence, value, difficulty, interest and effort, and statistical literacy of 200 public senior high school students selected through stratified random sampling. The SATS-36© developed by Schau et al. (2003) was used to determine attitudes, while a researcher-made questionnaire was utilized to measure statistical literacy. Using descriptive statistics and inferential analysis, students' attitudes toward the subject were established positively in value, interest, and effort components. In contrast, a negative attitude was exhibited in the components of affect, cognitive competence, and difficulty. Students' statistical literacy was found to be low in all areas and as a whole. Among the six components of attitude, the value component showed a significant relationship and predicted students' statistical literacy. Thus, the most vital component of attitudes toward statistics is value.

A STRUCTURAL EQUATION MODEL INVESTIGATING THE IMPACT OF TERTIARY STUDENTS’ ATTITUDES TOWARD STATISTICS, PERCEIVED COMPETENCE AT MATHEMATICS, AND ENGAGEMENT ON STATISTICS PERFORMANCE

Research in the field of statistics teaching has gained momentum, with numerous studies reporting that attitudes towards statistics are related to student performancein a statistics course. The aim of this study was to explore the effects of students’attitudes toward statistics, students’ perceived competence at mathematics, and students’ engagement in the learning process on their overall performance in a tertiary statistics course. The Survey of Attitudes Toward Statistics (SATS-28) was administered to 170 tertiary Early Childhood Education students in a large university in Greece. A Structural Equation Model was generated,and a confirmatory factor analysis was performed resulting in a three-component structure being accepted. Path analysis revealed direct links between perceived competence at mathematics and the three attitudes components, as well as a direct effect of perceived competence at mathematics on students’ performance in the statistics course. Engagement in the learning process also had a direct impact on students’ performance. First published June 2020 at Statistics Education Research Journal Archives

ASSESSING STATISTICS ANXIETY IN AN ONLINE OR HYBRID SETTING: THE ADAPTION AND DEVELOPMENT OF A NEW INSTRUMENT SASOH

With the purpose of developing an instrument for measuring statistics anxiety in the online or hybrid setting, this study tested the newly developed instrument in two stages. Results on item selection and exploratory factor analysis based on pilot testing (n = 115) are presented. Results on classical item analysis, the confirmatory factor analysis, the measurement invariance test results, and the predictive and discriminant validity of the final model based on formal testing (n = 709) are presented. The resulting Statistics Anxiety Scale in the Online or Hybrid setting instrument (SASOH) has 27 items and four dimensions. The four dimensions are Class and Interpretation Anxiety (CI), Fear of Asking for Help Anxiety (FA), Online System Anxiety (OS), and Pre-Conception Anxiety (PC). The results of the confirmatory factor analysis revealed that the four-factor SASOH model represents an adequate description of statistics anxiety in an online or hybrid setting. Moreover, multiple-groups confirmatory factor analysis affirmed that the resulting model achieved at least partial measurement and structural invariance across gender and program. In addition, attitudes toward statistics significantly predicts the four factors of statistics anxiety, and the discriminant validity from mathematics anxiety was confirmed. Recommendations for future studies are also provided.

Psychometric Evaluation of the Students’ Attitudes Toward Statistics and Technology Scale (SASTSc)

We sought to evaluate the SASTSc in two samples of students taking a statistics course that incorporates statistical software. The SASTSc was given at two time points, once at the beginning of the semester and then again at the end of the semester. Our evaluation included examining competing factor analytic models, examining convergent validity, test-retest reliability, and assessing internal consistency. Our results in both samples replicate the scale’s proposed factor structure; however, not all items were useful and we propose some changes to the wording of items to improve the scale.

Validation of an Adapted Version of the Statistical Anxiety Scale in English and Its Relationship to Attitudes Toward Statistics

The aims of this study were to validate an instrument that measured statistics anxiety and to examine how attitudes toward statistics predict statistics anxiety using the Attitudes Toward Statistics (ATS) Scale for a sample of 323 undergraduate social science majors enrolled in colleges and universities in the United States. A confirmatory factor analysis suggested retaining a revised two-factor model of the Statistical Anxiety Scale (SAS) to measure statistics anxiety, namely, help and interpretation anxiety ([Formula: see text] = 49.37, df = 38.13, p = .105, comparative fit index [CFI] = .959, standardized root mean square residual [SRMR] = .035, root mean square error of approximation [RMSEA] = .076). An examination of discriminant validity of the scores of the SAS with scores of the ATS subscales revealed that statistics anxiety and attitudes toward statistics are distinct constructs. Structural equational modeling was used to determine whether attitude toward course and attitude toward field were predictors of examination anxiety and asking for help anxiety. Of the two factors of the ATS scale, attitudes toward field and attitudes toward course, the latter predicted examination anxiety better than the former did, although both were moderate predictors of examination anxiety. We recommend that statistics educators consider the role of statistics anxiety as well as attitudes toward statistics and the field when designing their pedagogical approach.

Using Distributed Practice to Improve Students’ Attitudes and Performance in Statistics

Background: Research shows distributed practice enhances learning and skill development, but less is known about the effect on perceptions and attitudes toward the material being learned. Objective: This study examined whether distributed practice could improve performance and attitudes in statistics, a subject that students report finding unpleasant and anxiety-provoking. Method: This quasi-experiment compared statistics students who received distributed practice with Excel throughout the semester to a control group without distributed practice. At the end of the semester, all students completed a major data analysis project with Excel and a self-report measure of their perceptions and attitudes toward the class and statistics. Results: Significant results suggest students who received distributed practice: earned higher project grades; liked statistics more; and perceived the class to be more effective for knowledge and skill development, even though they found statistics to be more difficult than the control group. Conclusion: This study suggests distributed practice helps improve students’ performance and attitudes toward statistics, even though they think it is difficult. Teaching Implications: In addition to improving performance in challenging subjects, distributed practice may be used to help students appreciate and feel more favorably about classes they find difficult.

Measuring Statistics Attitudes at the Student and Instructor Levels: A Multilevel Construct Validity Study of the Survey of Attitudes Toward Statistics

Numerous studies have been conducted using the Survey of Attitudes Toward Statistics-36 (SATS-36). Recently, large-scale assessment studies have begun to examine the extent to which students vary in their statistics attitudes across instructors. Yet, empirical evidence linking student responses to the SATS items to instructor-level constructs is still lacking. Using multilevel confirmatory factor analysis, we investigated the factor structure underlying the measure of students’ statistics attitudes at both the student and instructor levels. Results from 13,507 college students taught by 160 introductory statistics instructors support a correlated six-factor model at each level. Additionally, there is evidence for the structural validity of a shared teacher–student attitude impacts construct that may capture meaningful patterns of teaching characteristics and competencies tied to student development of statistics attitudes. These findings provide empirical support for the use of the SATS-36 in studying contextual variables in relation to statistics instructors. Implications for educational practice are discussed.