An On-Line Virtual Environment For Teaching Statistical Sampling And Analysis

Abstract

Regardless of the related discipline, students in statistics courses invariably have difficulty understanding the connection between the numerical values calculated for end-of-the-chapter exercises and their usefulness in decision making. This disconnect is, in part, due to the lack of time and opportunity to actually design the experiments and collect the data. The prototypes proposed in this project were developed to allow students to design experiments and collect data in relevant settings without the impediments to real data collection. The virtual environments attempt to replicate real situations of interest in which students can design and run experiments, devise alternative sampling strategies, analyze the results of experiments, and relate the result to the original experiment. The setting and underlying data set detailed in this paper were developed to allow students to experience a wide range of statistical concepts typically found in introductory statistic courses, such as basic descriptive statistics, estimation, hypothesis testing, ANOVA, and regression. Assessments of student knowledge after using this approach have shown marked increases in students understanding of statistical concepts, especially confidence intervals and hypothesis testing. Specific details about the data set are provided as are suggestions for using it in an introductory statistics class. Potential uses and examples for a variety of disciplines are also included.