This is the core of the experimental design unit and may take more than a week for you to complete. Here we cover the basic experimental designs:

1. Completely randomized design,
2. Randomized complete block design,
3. Latin Square design,
4. Factorial treatments in a completely randomized design, and
5. Factorial treatments in a randomized compete block design.

In each case we will examine the assumptions being made, the general protocol and the general linear model that will be assumed for the analysis. After a couple of these you will see a pattern emerge in both the design aspects and the analysis aspects that should help you extrapolate to more complex situations.

Finally we will work through the estimation and testing of treatment effects. This is particularly important with factorial treatments where we wish to separate the main effects of each factor from the interaction effects between factors. This represents a further extension of the discussion on linear contrasts and multiple comparisons held at the end of unit three.

Randomized complete block design (PowerPoint or PDF)

Latin Square design (PowerPoint or PDF)

Factorial treatments (PowerPoint or PDF)