Statistics in Experimental Design (ANOVAs)




Objectives:

The course concentrates on the analysis of data obtained from experiments in the behavioral sciences, especially psychology. Major emphasis is placed on analysis of variance techniques going from simple single-factor independent group designs to multiple-factor designs involving both between- and within- subject manipulations. General rules are stressed.

After completing this course, students will be able to:

  1. Think critically about the application of experimental and quasi-experimental designs in psychological research
  2. Use computers to conduct analyses and interpret their output
  3. Understand and apply appropriate statistical analyses for different types of experimental designs
  4. Apply data analysis skills to research in different areas of psychology

Text:

  • Keppel, G., & Wickens, T. D. (2004). Design and Analysis: A Researcher's Handbook (4th ed.). Upper Saddle River, NJ: Pearson Prentice Hall. (available at Norris Center bookstore).
  • Other assigned articles or handouts available through this web site or in class

Class Meetings:

  • Tuesdays and Thursdays: 9:30 - 10:50 AM
  • Harris - Room 205

Requirements:

  • An objective midterm exam near the middle of the term (October 21)
  • An objective final exam (during the university final exam period)
  • Weekly homework sets (Posted and due each Thursday starting the second week of class)

Grading:

  • Homework - 40%
  • Midterm Exam - 30%
  • Final Exam - 30%
Note:

The documents below are in PDF format. You will need a reader program, such as Adobe Acrobat to read them. If you do not have such a program, a free version is available here

If you woud like to print multiple pages of the PDF file onto one printer page, here are instructions for some printers (note that some slight modification might be required depending on printer used):

  1. When in the PDF, click on the printer icon at the top of the page
  2. Click on the PROPERTIES button in the box that has appeared
  3. Change the PAGES PER SHEET to be whatever you prefer
  4. Click OK on the box that you made pop up by hitting PROPERTIES
  5. Click OK on the box that you made pop up by hitting the printer icon
You will be abe to save considerable pages this way and still use the PDF format.
Course Outline:
WeekTopicCourse NotesReadingProblem Sets and Data
Week 1
  • Introduction to the course
  • Experimental method
  • randomization
  • independence
  • null hypotheses

  • Thursday
  • Syllabus
  • Chapter 1
  • N/A
    Week 2
    • null hypotheses
    • partialing variance
    • F-distributions
    • Comparing F distributions with other distributions
    • Comparison of ANOVA with other methods
  • Tuesday
  • Thursday
  • Chapter 2
  • Chapter 3
  • Problem Set #1
  • SPSS Data #1
  • Week 3
    • Assumptions made by the ANOVA
    • What to do when the assumptions don't hold
    • Effect Size
    • Power
    • Meaning of positive and negative results
  • Tuesday
  • Data Set for 10/5
  • Output from data set for 10/5
  • Thursday
  • Chapter 7
  • Tukey's Ladder of Powers Handout
  • Tabachanick and Fidell recommendations
  • Chapter 8
  • Wilkinson Article
  • Cohen Article
  • Problem Set #2
    Week 4
    • Anaytic, Planned Comparisons
    • Trend Analysis
  • Tuesday
  • Thursday
  • Chapter 4
  • Chapter 5
  • Problem Set #3
    Week 5
    • Simultaneous Comparisons
    • Midterm Examination - Thursday
  • Tuesday
  • Exam Solutions
  • Chapter 6
  • N/A
  • N/A
    Week 6
    • Introduction to Factorial Design
    • Two Factor Designs
    • Main Effect Calculations
    • More on Main Effects
    • Simple Effects
  • Tuesday
  • Thursday
  • Chapter 10
  • Chapter 11
  • Chapter 12
  • Problem Set #4
    Week 7
    • More on Interactions and Calculations
    • General Linear Model
    • Unequal Sample Sizes
  • Tuesday
  • Thursday
  • Chapter 13
  • Chapter 14
  • Problem Set #5
    Week 8
    • Analysis of Covariance
    • Single Factor Within Subjects Design
  • Tuesday
  • Thursday
  • Chapter 15
  • Chapter 16
  • Problem Set #6
    Week 9
    • Further Within Subjects Topics
    • Two-Factor Within-Subjects Designs
  • Tuesday
  • Thursday
  • Chapter 17
  • Chapter 18
  • Problem Set #7 - Due Tuesday, 11/30
    Week 10
    • Mixed Design: Overall Analysis
    • No Class Thursday - Thanksgiving
  • Tuesday 

  • Chapter 19
  • N/A
    Week 11
    • Mixed Design: Analytical Analyses
    • Catch Up / Review / Further Topics
  • Tuesday
  • Thursday 
  • Chapter 20
  • Chapter 26 (?)
  • N/A
    Final Exam
    • Monday, December 6, 2004
    • 12:00 - 2:00 P.M.




    References:

    • Cohen, J. (1992). A power primer. Psychological Bulletin, 112, 155-159.
    • Tukey, J. W. (1977). Exploratory Data Analysis. Reading, MA: Addison-Wesley Publishing Company.
    • Tabachnick, B. G., & Fidell, L. S. (1996). Using Multivariate Statistics. (3rd ed.). New York: Harper Collins.
    • Wilkinson, L., & APA Task Force on Statistical Inference. (1999). Statistical methods in psychology journals: Guidelines and explanations. American Psychologist, 54, 594-604.

    Work Mentioned in Class:

    • Cohen, J. (1962) The statistical power of abnormal-social psychological research: a review. Journal of Abnormal and Social Psychology 69, 145-153.
    • Cohen, J. (1988) Statistical Power Analysis for the Behavioral Sciences. (2nd ed). Mahwah, NJ: Lawrence Erlbaum.

    Some Other Useful Resources with Information on Statistics in Experimental Design:

    • Abelson, R. P. (1995). Statistics as Principled Argument. New Jersey: Lawrence Erlbaum Associates.
    • Hays, W. L. (1994). Statistics (5th ed.). Fort Worth, TX: Harcourt Brace College Publishers.
    • Howell, D. C. (2001). Statistical Methods for Psychology (5th ed.). Belmont, CA: Duxbury Press.
    • Kirk, R. E. (1995). Experimental Design: Procedures for the Behavioral Sciences. (3rd ed.). Pacific Grove, CA: Brooks/Cole.
    • Kuehl, R. O. (2000). Design of Experiments: Statistical Principles of Research Design and Analysis (2nd ed.). Pacific Grove, CA: Duxbury Press.
    • Maxwell, S. E., & Delaney, H. D. (2004). Designing Experiments and Analyzing Data: A Model Comparison Perspective. (2nd ed.). Mahwah, NJ: Erlbaum.
    • Neter, G., Kutner, M. H., Nachtsheim, C. J., & Wasserman, W. (1996). Applied linear statistical models (4th ed.). Boston, MA: McGraw-Hill.
    • Pedhauzer, E. J., & Pedhauzer Schmelkin, L. (1991). Measurement, Design, and Analysis: An Integrated Approach. Hillsdale, NJ: Erlbaum.
    • Rosenthal, R., & Rosnow, R. L. (1991). Essentials of Behavioral Research: Methods and Data Analysis (2nd ed.). Boston, MA: McGraw-Hill.
    • Schinka, J. A., & Velicer, W. F. (2003). Handbook of Psychology - Volume 2: Research Methods in Psychology. Hoboken, NJ: John Wiley.
    • Winer, B. J., Brown, D. R., & Michels, K. M. (1991). Statistical Principles in Experimental Design (3rd ed.). Boston, MA: McGraw-Hill.
    Comments