Statistical analysis techniques and experimental desing methods are taughted in this class. Experimental design methods include between-subject designs, within-subject designs, mixed-factors designs, randomized block design, latin-square design, hierarchical design, central composite designs and some other efficient experimental designs. Analysis of variances is the main analysis techniques along with response surface methodology and regression analysis.

Homework 20%
Term Project 20%
Mid-term 30%
Final 30%

Winer, B.J., Brown, D. R., and Michels, K.M.: Statistical principles in experimental design (3rd eds) McGraw Hill (1991)

 Introduction to experimental design
 Design classification
 Between-subjects design
 Randomized-Block design
 Comparisons
 Within-subjects design
 Mixed-factors design
 Fractional-factorial design
 Empirical model
 Introduction to response surface methodology
 Central composite design
 Sequential experimentation
 Introduction to nonparametric analysis (If time is available)
 One-sample case analysis
 Two-sample case analysis
 K-sample case analysis

Topics for Term Project

1. How do we conduct the power analysis?
2. How many subjects should be used in a human factors experiment?
3. What significance level should be used in analyzing the data and why?
4. What experimental designs (e.g., within-subjects, between-subjects, mixed-factors designs) should be used?
5. Comparison of uni-variate and multi-variate analyses.
6. Efficient experimental designs
7. Quasi-experimental designs
8. Comparison of Tacuchi and fractional-factorial design
9. How do we determine whether the data from a specific subject should be eliminated or not.
10. When do we use parametric analysis or non-parametric analysis?
11. How do we know whether the assumptions for the ANOVA are satisfied or not?
12. Data analysis techniques (e.g., Factor Analysis, Principal Component Analysis, Independent Component Analysis, Meta Analysis, Correlation Analysis, Nonlinear Regression Analysis, Analysis of Residual, etc.)
13. Analysis techniques using fuzzy concepts
14. Why should we do randomization in the experiment and how?
15. To what extent can we generalize the experimental results?
16. Comparison of ANOVA and regression analysis.
17. Comparison of post-hoc analysis techniques (Bonferonni t, Duncan, SNK, Tukey, etc.)
18. Nonparametric analysis techniques.