Shapesplosion is an on-line game in which a person is expected to place specifically shaped pegs into the appropriate holes within a short time period. In this project, students are asked to use the Shapesplosion game to design an experiment and collect data. This game is specifically designed so that students have the opportunity to develop and test their own unique research question.
You can leave all the variables blank when you are simply trying out the game, however, if you want to find your score is the database of results, you will need to select the Participant Info box.
The following link allows you to play the Shapesplosion Game.
Many browsers will require you to allow popups and allow adobe flash before they will run these stat2labs games.
In the following activities, students will have the opportunity to design and analyze an experiment. They will:
- Formulate a hypothesis test about the number of items subject can remember
- Determine how to collect data that best addresses their research question.
- Collect data
- Check model assumptions
- Analyze the data
- Draw conclusions within the context of their study
This activity is designed to help introductory statistics students collect their own data and apply it to a regression analysis.
2-sample t-tests or paired t-test: Student Handout
This activity is designed to build upon students' knowledge of t-tests to a fun application that emphasizes the differences between 2-sample t-tests or paired t-tests.
Instructors Notes for Research Project:
Prerequisites: This lab can easily be done as a 2-sample t-test or a paired t-test using one explanatory variable. If students are planning to conduct a multifactor experiment, they should read and answer questions from Chapter 4: Design of Experiments. This chapter is freely available for class testing. More complex designs, such as repeated measure designs, are discussed in Chapter 5.
Research Project Materials:
- Computer lab space is needed to conduct the experiment, which can be done inside or outside of the regularly scheduled class time.
- In any experiment involving humans, Institutional Review Board approval should be received from your institution. It may be best to receive a general approval for all Shapesplosion experiments in your course. Even if you do receive general approval, it may be appropriate for the students to prepare an IRB proposal as a class assignment, even if it is not sent to the board.
- The article by Stroop, ”Studies of Interference in Serial Verbal Reactions”, Journal of Experimental Psychology, 18,643-662, can be found on-line at http://psychclassics.yorku.ca/Stroop/ or other library resource for your class such as http://www.apa.org/psycinfo/.
- Assign each student (or group of students) one student ID and decide before class what course ID you plan on using. Any alphanumeric code without spaces is acceptable. However, human responses should be confidential and actual names should not be used as student IDs. You may want to search the database to determine if a course ID has already been used.
- Other materials may be needed depending upon student design.
- Experience statistics as it is practiced by researchers in psychology:
Develop a systematic model for development of an experimental design:
- Collect data appropriate to a specified purpose, and recognize limitations in existing data.
- Explain the benefits of the statistical approach to design of experiments and use it.
- Analyze data using appropriate graphs and numerical tools (primarily ANOVA).
- Derive appropriate, actionable conclusions from data analysis.
- Present results and conclusions in both technical and non-technical terms, in writing and orally.
- Describe the role of statistical thinking and methods for problem solving.
- Discuss the value of understanding, quantifying, and reducing variation.
- Develop an understanding of how statistics is integral to research in cognitive psychology.
- Determine the appropriate questions statistical consultants should ask.
- Develop the ability to read scientific literature.
Paper Review: I have found that some students are initially frustrated or intimidated when they are asked to read a research paper outside of their major. In my experience, providing more time to read the paper has not been helpful. It may, however, be appropriate to:
- Clarify that the paper review questions are worth only a small amount of the overall grade
- Allow students to complete the assignment in groups
- Allow students to turn in a revised version of their paper review questions after they are discussed in class.
Class Discussion: I suggest spending at least part of three separate class periods to discuss the Stroop (1935) paper and develop a class project or several group projects. It is helpful to initially identify that your goal as a professor is not to be able to answer all of their questions about current research in cognitive psychology, but to teach them a process in which they can find their own answers.
You may want to consider additional discussion topics:
- You can instruct the students to go to the library and read a chapter on attention, memory, or reaction time from any introductory psychology book. Ask them to identify some of the factors that could influence reaction time.
- You may want to discuss the Woodworth Wells Color Sheet before the students read the paper by Stroop.
- If you want students to find their own research papers on reaction time tests, PsycINFO is a good psychology resource.
Step 1: Spend at least 20 minutes discussing the paper review questions. Students may not feel qualified to design a psychology study, but they often can suggest appropriate modifications to a given study. Start students thinking about their own primary research questions and ask them:
- How would you design a test to answer these questions?
- Which factors and what levels could be used?
- Which questions relate to main effects and which relate to interaction effects?
- How can you design an experiment that is general enough to be of scientific interest, but specific enough that it can be conducted within a lab in a few weeks time?
Step 2: Invite a psychologist to the class (or a statistician if you are a psychologist) to answer student questions that are beyond your scope of knowledge.
- It was very helpful for my students to hear from a researcher that he/she did not know all of the answers to their questions.
- My students seemed to be somewhat surprised that they could contribute to science by conducting an experiment that has never been specifically studied before. Having a scientist in each field enforce the idea that science in not just a collection of facts but an ongoing exploratory process was very helpful for my students.
Step 3: After students have submitted their experimental ideas, the class can vote on one experiment to conduct as an entire class. This allows you to test more factors and levels with replicates in less time. However, each group of students could just as easily design and analyze their own experiments.
It is beneficial to talk about scale-attenuation effects (i.e. floor or ceiling effects) before students finalize their design. If the subjects rarely finish before the timer expires (i.e. the dependant variable is almost always at the highest time level), no differences will be seen between the conditions (even if one truly exists). While students may not consider it as fun as the other options, "no time limit" provides the most straightforward response variable to analyze.
One related topic not discussed in the listed research papers is how stress can impact reaction time. The students can calculate the average time per piece and determine if a time limitation of "short", "medium", "long", or "no time limit" impacts there average time per piece.
Final Paper or Poster Discussion: During the in-class review day, spend some time discussing how the process details (which are rarely discussed in textbooks and are often only given cursory comments in research papers) can significantly impact the analyses and conclusions of the data. My students are typically surprised by:
- The amount of time and effort needed to appropriately conduct experiments
- The numerous occasions in which an experiment can so easily become biased
Grading: I would suggest 50 points for the entire project (this is the same value as an exam in my course).
- 5 points for Day 1, the review of Stroop's paper
- 10 points for Day 2, experimental design
- 5 points for lab procedures
- 5 points for appropriate comments and suggestions on other student papers
- 25 points for the final paper or poster
If your institution does not have an Institutional Review Board, you can find more information on registration as well as educational materials at http://www.hhs.gov/ohrp/
Thanks to Tietronix software, Sam Rebelsky, and Grinnell MAP students Betsy Lorton, Sarah Marcum, Arunabh Singh, Andrew Applebaum, Alex Cohn, Nathan Levin, Jeffrey Thompson for creating, editing and maintaining the on-line game.