The t-test and analysis of variance (ANOVA) are two of the most common statistical techniques used in practice. These techniques allow researchers to statistically assess the plausibility that a feature of a population differs from a hypothesized value on average, or that two or more samples or groups differ in terms of an outcome of interest. For example, grain yields could be compared under different fertilizer treatments. Inference is conducted at the population level on the basis of sample data.
This short course is designed to provide an overview of these approaches. Concepts and caveats underlying hypothesis testing will be reviewed. The t-test portion will include one-sample, two-sample, and paired tests. ANOVA can be used to compare more than two groups. This test and its variations (i.e. two-way ANOVA and ANCOVA) will be covered as well. Course coverage includes these methods’ underlying assumptions, how to check for them, and procedures for some cases when the assumptions are not met. Datasets will be either simulated or built into R, such as the iris dataset. Code for this data, graphics, and the demonstration will be available. This lecture will focus on the mechanics and concepts underlying t-tests and ANOVA.