Journal Article

  • Learning statistics requires learning the language of statistics. Statistics draws upon words from general English, mathematical English, discipline-specific English and words used primarily in statistics. This leads to many linguistic challenges in teaching statistics and the way in which the language is used in statistics creates an extra layer of challenge. This paper identifies several challenges in teaching statistics related to language. Some implications for the effective learning and teaching of statistics are raised and methods to help students overcome these linguistic challenges are suggested.

  • The test instrument GOALS-2 was designed primarily to evaluate the effectiveness of the CATALST curriculum. The purpose of this study was to perform a psychometric analysis of this instrument. Undergraduate students from six universities in the United States (n=289) were administered the instrument. Three measurement models were fit and compared: the two-parameter logistic model, the mixed model (comprised of both the two-parameter logistic and the graded-response model), and the bi-factor model. The mixed model was found to most appropriately model students’ responses. The results suggested the revision of some items and the addition of more discriminating items to improve total test information.

  • Self-efficacy and knowledge, both concerning the chi-squared test of independence, were examined in education graduate students. Participants rated statements concerning self-efficacy and completed a related knowledge assessment. After completing a demographic survey, participants completed the self-efficacy and knowledge scales a second time. Individuals with and without prior experiences with the topic were compared; those with prior experiences gave significantly higher self efficacy ratings and had higher demonstrated knowledge scores, although the latter difference was not statistically significant. While self-efficacy and knowledge scores did not differ significantly between the two administrations, individuals without prior topic experience saw greater improvements in self-efficacy calibration. Findings suggest that self-efficacy calibration may be improved through completing an assessment.

  • Statistics anxiety is a common problem for graduate students. This study explores the multivariate relationship between a set of worry-related variables and six types of statistics anxiety. Canonical correlation analysis indicates a significant relationship between the two sets of variables. Findings suggest that students who are more intolerant of uncertainty, believe that worry is beneficial, possess a negative approach to problems, and utilize cognitive avoidance as a coping strategy are more likely to have higher levels of the six types of statistics anxiety. These results highlight the complexity of graduate students’ statistics anxiety. Suggestions for intervention are discussed.

  • Many recent improvements in pedagogical practice have been enabled by the rapid development of innovative technologies, particularly for teaching quantitative research methods and statistics. This study describes the design, implementation, and evaluation of a series of specialised computer laboratory sessions. The sessions combined the use of an online virtual world, cloud collaboration technology, and a statistical package in order to simulate the entire data investigative cycle. The sessions covered multiple topics, research designs, and data analysis techniques relevant to psychology. Quantitative and qualitative feedback data regarding students’ perceptions of the sessions were analysed. The results demonstrate promising support for the use of Island-based sessions, but improvements and further research will be required.

  • Results from a study of 16 community college students are presented. The research question concerned how students reasoned about p-values. Students' approach to pvalues in hypothesis testing was procedural. Students viewed p-values as something that one compares to alpha values in order to arrive at an answer and did not attach much meaning to p-values as an independent concept. Therefore it is not surprising that students often were puzzled over how to translate their statistical answer to an answer of the question asked in the problem. Some reflections on how instruction in statistical hypothesis testing can be improved are given.

  • The recent introduction of statistics into the Brazilian curriculum has presented a multi-problematic situation for teacher professional development. Drawing on research in the areas of teacher development and statistical inquiry, we propose a Teacher Professional Development Cycle (TPDC) model. This paper focuses on two teachers who planned a lesson in collaboration with other teachers, implemented the lesson, and then reported on the implementation. Results indicate that the TPDC model has the potential to begin to upskill teachers with multi-dimensional development needs. TPDC provides an environment for helping teachers overcome their current beliefs and attitudes towards statistics and statistics teaching. The implications of our TPDC model for improving teachers’ practice in statistics are discussed.

  • How does the student untrained in advanced statistics interpret results of research that reports a group difference? In two studies, statistically untrained college students were presented with abstracts or professional associations’ reports and asked for estimates of scores obtained by the original participants in the studies. These estimates were converted to inferred effect sizes and compared with the actual effect sizes. Inferred effect sizes substantially overestimated actual effect sizes for all reports, a phenomenon dubbed the tall-tale effect. The effect was obtained with a variety of reports and statistics. The tall-tale effect could be controlled somewhat with simple changes in wording. This finding suggests a program of research which would better calibrate inferences with those actually obtained in the research.

  • Statistics education reform efforts emphasize the importance of informal inference in the learning of statistics. Research suggests statistics teachers experience similar difficulties understanding statistical inference concepts as students and how teacher knowledge can impact student learning. This study investigates how teachers reinvented an informal hypothesis test for categorical data through the framework of guided reinvention. We describe how notions of variability help bridge the development from informal to formal understandings of empirical sampling distributions and procedures for constructing statistics and critical values for conducting hypothesis tests. A product of this paper is a hypothetical learning trajectory that statistics educators could utilize as both a framework for research and as an instructional tool to improve the teaching of hypothesis testing

  • This study explored the use of two different types of collaborative tests in an online introductory statistics course. A study was designed and carried out to investigate three research questions: (1) What is the difference in students’ learning between using consensus and non-consensus collaborative tests in the online environment?, (2) What is the effect of using consensus and non-consensus collaborative tests on students’ attitudes towards statistics?, and (3) How does using a required consensus vs. a non-consensus approach on collaborative tests affect group discussions? Qualitative and quantitative methods were used for data analysis. While no significant difference was found between groups using the two collaborative testing formats, there was a noticeable increase in students’ attitudes across both formats towards learning statistics. This supports prior research on the benefits of using collaborative tests in face-to-face courses.