Statistical analysis and experimental design
Overview
This week-long course is aimed at people with little or no experience using statistical analyses in research. It introduces participants to core concepts in statistics and experimental design, aimed at ensuring that the resulting data is able to address the research question using appropriate statistical methods.
The interactive course gives participants a hands-on, applied foundation in statistical data analysis and experimental design. Group exercises and discussions are combined with short lectures that introduce key theoretical concepts. Computational methods are used throughout the course, using the R programming language. Formative assessment exercises allow participants to test their understanding throughout the course and encourage questions and critical thinking.
By the end of the course participants will be able to critically evaluate and design effective research questions, linking experimental design concepts to subsequent statistical analyses. It will allow participants to make informed decisions on which statistical tests are most appropriate to their research questions. The course will provide a solid grounding for further development of applied statistical competencies.
During this course you will learn about:
- One and two sample hypothesis tests
- ANOVA
- Simple linear Regression
- ANCOVA
- Linear Models
- Model selection techniques
- Power Analyses
- Practices in experimental design that lead to high quality research
- What to do with more advanced analysis techniques for experiments with unusual or complex designs
- How to take power analysis into consideration in your experimental design
- How to implement piloting in your experiments
After this course you should be able to:
- Analyse datasets using standard statistical techniques
- Know when each test is and is not appropriate
- Link experimental design to your statistical analysis strategy
- Formulate good research questions
- Identify common design pitfalls, and how to avoid or mitigate them
- Operationalise variables effectively
- Identify and deal with confounding variables and pseudoreplication
Target Audience
The course is aimed at people at postgraduate level who are involved in research.
Applicants are expected to have a working knowledge of R and must complete a prerequisite quiz as part of the registration process.
The course is open to Postdocs and Staff members from the University of Cambridge, Affiliated Institutions and other external Institutions or individuals.
Prerequisites
Working knowledge of R and the tidyverse package (assessed through a short quiz provided before acceptance on the course).
This course is not suitable for people who have completed either the Core Statistics or Experimental Design for Statistical Analysis courses, since significant portions of the course borrow from these stand-alone courses.
Exercises
Exercises in these materials are labelled according to their level of difficulty:
| Level | Description |
|---|---|
| Exercises in level 1 are simpler and designed to get you familiar with the concepts and syntax covered in the course. | |
| Exercises in level 2 combine different concepts together and apply it to a given task. | |
| Exercises in level 3 require going beyond the concepts and syntax introduced to solve new problems. |