Teaching

  • The ability to design experiments in an appropriate and efficient way is an important skill, but students typically have little opportunity to get experience. Most textbooks introduce standard general-purpose designs, and then proceed with the analysis of data already collected. In this paper we explore a tool for gaining design experience: computer based virtual experiments. These are software environments which mimic a real situation of interest, and invite the user to collect data to answer a research question. The following prototype environments will be described: an industrial process that must be optimized, a greenhouse experiment to compare the effect of different treatments on plant growth, and an arcade style applet that illustrates the use of t-tests, regression and analysis of variance. These environments are parts of a collection called env2exp, and can be freely used over the web. They have been used in several courses over the last two years.

  • Almost every day we come across statistics in our newspapers. Understanding these figures correctly not only gives us a better understanding of our social environment but also helps to prevent us from being taken in by misleading advertisements. This project investigates the teaching and learning of statistics through the use of statistical figures commonly found in newspapers and other mass media. These statistics have been used in specially designed courses such as "How to Read Figures in the Newspapers," a general education course offered to undergraduate students with or without a statistics background. Students find the topics interesting and appreciate the wide-ranging applications of statistics in different areas.

  • Statistical literacy should be a key goal in preparing students to understand statistical information which is often reported in the media. This research is centred on the teaching of a specially designed unit of work on statistical literacy to ninety Year 10 (14-year-old) high school students that emphasised media reports both in the teaching approach and in the pre- and post- assessments. The students' test responses were analysed using the SOLO taxonomy framework for assessment and results were compared to those in previous studies. The issues that arose in the development of the teaching unit, the preliminary results on changes in levels of statistical literacy observed, and the factors that could affect the development of statistical literacy, such as mathematical and English ability, are briefly reported. The students' and teachers' reactions to the unit of instruction using media reports are also discussed.

  • The widespread international adoption of DNA technology in forensic science over the last twenty years or so has resulted in some standardised methods of data collection and data interpretation. The impetus generated by the systematic approach characteristic of forensic DNA has carried into other fields of forensic science, typically resulting in forensic scientists wondering whether the same approaches can be applied to their own specialisms. Workers in areas of forensic interest such as ballistics and trace evidence have for some time collected in a systematic manner data connected with those fields. However there are many more areas of forensic science which require large bodies of systematically collected data. Some of these areas are so rarely used in forensic science that the required data is not available, and for a few areas of evidence it is infeasible, if not impossible to collect suitable data.

  • Over the last decade, the use of real world projects in introductory statistics courses has increased in popularity. Real world projects provide students with an opportunity to learn the entire process of a statistical investigation. Such projects fit the principles of active learning well. However, due to the time and effort required by both the instructor and students, it is difficult to sustain the project activity for a long time period. Hence, the final project reports are often disappointing. Through an NSF funded project, we have constructed a real-time online database. Students collect their own data and enter it into the database. Various activities are now available at http://stat.cst.cmich.edu/statact/. We assign group projects using the data collected by the students themselves. This paper shares how the process of statistical investigation is implemented into the project by using the students' own data.

  • Modern teaching methods require students to be active participants in the learning process. Assigning projects to students sets a frame which cultivates the interactivity between the instructor and the students and motivates the students to explore the field. The objective of this paper is to present the results from the use of individual directed projects in the introductory statistics course at the Department of Political Sciences of Aristotle, University of Thessaloniki. We compare this group with another group of students who were taught the introductory statistics course with conventional methods. The results indicate that students in the project-based group grasped statistical concepts and ideas at a higher rate than students in the control group, had a better attitude towards statistics, and did not think that statistics is as hard to learn as students in the other group.

  • We identify the student characteristics most associated with success in an introductory business statistics class, placing special focus on the relationship between student math skills and course performance, as measured by student grade in the course. To determine which math skills are important for student success, we examine (1) whether the student has taken calculus or business calculus, (2) whether the student has been required to take remedial mathematics, (3) the student's score on a test of very basic mathematical concepts, (4) student scores on the mathematics portion of the ACT exam, and (5) science/reasoning portion of the ACT exam. The score on the science portion of the ACT exam and the math-quiz score are significantly related to performance in an introductory statistics course, as are student GPA and gender. This result is robust across course formats and instructors. These results have implications for curriculum development, course content, and course prerequisites.

  • Least squares regression is the most common method of fitting a straight line to a set of bivariate data. Another less known method that is available on Texas Instruments graphing calculators is median-median regression. This method is proposed as a simple method that may be used with middle and high school students to motivate the idea of fitting a straight line to data. The median-median line may also be viewed as a method that is not greatly affected by outliers (robust to outliers). Our paper briefly reviews the median-median regression method, considers various examples to compare the median-median line to the least squares line, and investigates the properties of the median-median line versus the least squares line using a simulation study.

  • Classical regression models, ANOVA models and linear mixed models are just three examples (out of many) in which the normal distribution of the response is an essential assumption of the model. In this paper we use a dataset of 2000 euro coins containing information (up to the milligram) about the weight of each coin, to illustrate that the normality assumption might be incorrect. As the physical coin production process is subject to a multitude of (very small) variability sources, it seems reasonable to expect that the empirical distribution of the weight of euro coins does agree with the normal distribution. Goodness of fit tests however show that this is not the case. Moreover, some outliers complicate the analysis. As alternative approaches, mixtures of normal distributions and skew normal distributions are fitted to the data and reveal that the distribution of the weight of euro coins is not as normal as expected.

  • The dataset presented here illustrates to students the utility of logistic regression. Its analysis results in a fit that explains much of how senators vote on a particular bill, and allows for quantification of the effects of ideology and money on the vote. A number of interesting quantitative interpretations follow from a good fit. A successful analysis makes use of a number of ideas discussed in applied courses: descriptive statistics, inferential methods, transformation of variables, and the handling of outliers and special cases. All these issues arise in the context of data on variables that require of students no specialized knowledge. Students have strong qualitative preconceptions about the relationships among the variables. The final results quantify, and nicely confirm, many of those conceptions.

Pages