Strategies for Educational Inquiry

Week 9: Experimental Designs - October 29

Announcement

Note: The Loftus (1975) article that we will discuss in class is available below. Other resources, such as the overheads, and additional readings, will be listed later in the week.

  Updated article critique form. The original handed out in class omitted the "hypothesis" section.

Class room overheads:

  Pre-Experimental Designs

  Experimental Designs

  Threats to Internal and External Validity

  1. Textbook and other Readings

    • Gay & Airasian 355-382

    •   Loftus, Elizabeth F. (1975). Leading questions and the eyewitness report. Cognitive Psychology, 7, 55-572.

  2. Overview of Experimental Design

      Michael, R. S. (2000). Experimental method and threats to internal validity.

  3. Remember, causation should not be inferred from correlation

      Games, Paul A. (1990). Correlation and causation: A logical snafu. Journal of Experimental Education, 58(3), 239-246.

    "The crucial difference between experiments and investigations (correlationsl studies) is that in experiments the process of random assignment guarantees that in the population there is no correlation between the experimental errors and the treatment effects. For an investigation to yield proper causative conclusions, it is necessary for the same condition to hold."

  4. Is experimental research externally valid?

      Anderson, Craig, A. Lindsay, James J., & Bushman, Brad J. (1999). Research in the the psychology laboratory: Truth or triviality? Current Directions in Psychological Science, 8, 3-9.

    "... [A]pplication-oriented scholars sometimes deride the psychological laboratory as a place where only trivial facts are to be found. In essence, the charge is that (some, most, or all) research from the psychological laboratory is externally invalid, and therefore pointless."

  5. Why do education researchers reject randomized experiments?

      Cook, Thomas D. (1999). Sciencephobia: Why education researchers reject randomized experiments Education Next, 1, 63-68.

    "The superiority of random assignment for drawing conclusions about cause and effect in nonlaboratory settings is routinely recognized in both the philosophy of science literature and in methods texts in health, public health, agriculture, statistics, microeconomics, psychology, and those parts of political science and sociology that deal with improving the assessment of public opinion."

  6. Research Randomizer

      Visit the Research Randomizer web site

    "This web site is designed to assist researchers and students who want an easy way to perform random sampling or assign participants to experimental conditions."

    The interested student should work through the tutorial. Highly recommended.