We developed this lab in an attempt to convey to students some basic elements of an experiment.
From a nontechnical description of an experiment, we want the student to be able to answer the following questions:
For the source of our narratives, we use excerpts of newspaper articles, accompanied by summaries of journal articles. By comparing and contrasting news and journal reports on an experiment, students hone their skills in critical thinking, synthesizing multiple sources and identifying important statistical elements.
Additional important lessons we expect students to take away from this lab address the importance of having comparison groups; randomization; blindness; and generalizing results to populations other than those studied.
We try to present experiments on interesting topics with unusual features or that offer important lessons on the above topics.
To begin, the lab starts with a brief set of instructions and a few sentences on the topic of the lab. Students are then presented with a set of experiments in the Topics window. The instructor can choose any number of practice rounds for the lab, and the experiments can be selected randomly for each student from a subset of those available for the lab.
To begin work on an experiment, the student selects an experiment from the topics window. This brings her to the main work area. The design is presented in the form of a tree. The different levels of the tree represent the different stages in the experiment --
When the student first sees the design, the boxes are empty. The task is to fill in the boxes in the tree with the details of the experiment by relating the content of the newspaper and journal articles to the different stages. They do this by identifying text in the articles that relates to the particular box they are working on.
When the student clicks on the phrase, it is entered into the box pictorially as an icon. All the phrases in the text relating to this icon are highlighted in the color of the box as if the student used a high-liter to mark important passages in the text. If the student selects text that doesn't go into the box, a message giving some indication why the match is inappropriate is displayed in the message bar at the bottom.
After completing the contents of the design, the student moves to the animation component of the experiment. Here the design is displayed in a cartoon-like way and the student sees the subjects - shown as little green faced fellows in figure participate in the experimental process. Some are rejected at the enrollment gate. Others move through the different stages being randomized in the centerfuge, treated in the blue box, and measured on the scale. Finally, the subjects fall into the appropriate histogram, adding their value to the appropriate bin.
Once the virtual experiment is complete, the student proceeds to answer questions about the design. The questions in the wrap--up of the experiment are not intended to be graded. They are grouped into pages, and the student submits one page of questions at a time. Her answers are checked immediately; a profile of the student is built from her responses; and she receives individualized and detailed comments to help clarify important issues before proceeding to the next page of questions.
Once finished with the practice rounds, she can move to the challenge round, where the goal is to design her own experiment. She is given a glossary of terms each identifying: a characteristic of the subject, a procedure for splitting the subjects into groups, a type of treatment, etc. She is also offered several designs for her experiment. Once the design is filled in, she runs the animation, which produces responses at random according to a simple model for biases and interactions that is determined by the design. Finally, after the virtual experiment is run, a news story that summarizes and critiques her design is dynamically generated.
This page was last updated on 09/26/98. Questions, comments, suggestions.