Course Description
Students will learn how to design effective, informed, experimental, and observational studies for field plant biology. The course will also cover statistical analyses and software to interpret and visualize those data.
Athena Title
Exp Design Field Plant Bio
Prerequisite
One undergraduate-level Statistics course
Semester Course Offered
Offered spring
Grading System
A - F (Traditional)
Course Objectives
By the end of this course, students will understand how to: 1) design hypothesis-informed studies that directly relate to planned analyses 2) implement appropriate analytical approaches 3) deal effectively with real-world heterogeneity in field studies 4) manage and visualize data responsibly
Topical Outline
1. Introduction to experimental design and statistical inference • Review of probability theory, distributions, and descriptive statistics • Data visualization: responsible data exploration and examining distributions 2. Designing successful field studies: philosophies and relationships to statistical inference • Experimental vs. observational study design • Dealing with heterogeneity in the real world: appropriate controls, replication, and pseudoreplication • Visualizing experimental designs and hypotheses • Responsible and effective data management strategies 3. General linear models (2 weeks) • Regressions, ANOVA, ANCOVA • Dealing with heterogeneity in the real world: data transformations • Correcting for multiple comparisons • Data visualization: discrete vs. continuous variables 4. Generalized linear models (2 weeks) • Binomial and Poisson families • Data visualization: back-transforming from link functions 5. Mixed models: fixed and random effects (2 weeks) • Dealing with heterogeneity in the real world: blocking, nesting, stratifying • Temporal vs. Spatial variation • Data visualization: how to deal with random effects 6. Multivariate analyses of community data (2 weeks) • Measuring distances among groups in multivariate space • Ordination techniques to reduce dimensionality: PCA, PCoA, CA, NMDS • Inference tools: PERMANOVA, ANOSIM, PERMDISP • Data visualization: visualizing multi-dimensional points and axes 7. Intro to structural equation models • Pros and cons of SEMs; difference vs. multiple regression • How to interpret a SEM figure 8. Intro to model selection and multi-model inference • Statistical philosophies: Information-theoretic approach • Responsible model selection: a priori hypotheses 9. Intro to Bayesian probability and inference • Statistical philosophies: Bayes theorem • Markov Chain Monte Carlo techniques • How to interpret results from Bayesian analyses
Syllabus