**21 - 23 May**

### Course Overview

This course provides a comprehensive hands-on introduction to regression analysis techniques The course content is designed for researchers with some prior knowledge of basic statistical testing, such as t-tests, p-values, confidence intervals and simple linear regression. The primary focus is on developing a conceptual understanding of regression models through numerous examples. There will be a strong emphasis on practical implementation in R, and interpretation of output. Approximately half the time will be dedicated to practical hands-on sessions.

The core content starts from linear models with more than one variable, enabling research questions like "What is the effect of this treatment/intervention after adjusting for confounding variables?" or "What is the relationship between two variables while controlling for other factors?"

We then cover interactions between variables in linear models, enabling research questions like: "How does the effect of the treatment depend on some other variable? Is the treatment effect different between groups?" and "How is the relationship between two variables modified by some other variable?"

Fundamental regression concepts and skills that arise in regression, like multicollinearity, multiple testing, model selection, generalizing the linear model to data that is non-normal (e.g., binary response and count data), and regression with non-linear relationships between variables, are all covered in this course.

By the end of this course, you will have a foundation in regression modelling techniques with the practical experience in R needed for more advanced regression methods like mixed models, longitudinal data analysis, survival analysis, meta-analysis, multivariate analysis, ordinal and multinomial regression, spatial regression and other extensions.

*Course Outline*

**Day 1:** Revision, Multiple Regression Introduction and Extensions

**Day 2:** Morning/Afternoon: Multiple Comparisons/Model Selection

**Day 3: **Morning/Afternoon: Generalized Linear Models (GLMs)/Generalized Additive Models (GAMs)

**Assumed Knowledge **

We assume knowledge of introductory statistics, including principles of study design, the concept of a p-value, the concept of a confidence interval, one-sample and two-sample t-tests, and the equivalence of a t-test to simple linear regression and simple linear regression (with a single dependent and single independent variable). All of these are covered in our Introduction to Statistics courses.

We also assume you have some experience with R. To enrol in this course, we ask you to complete a quick exercise. If you are new to R, you should complete our one-day introduction to R course prior to this course.

**Course Requirements:** You will need to bring and use your own computer during the course.

Presenter and Expertise: Peter Humburg, Biostatistician UNSW Stats Central

**Date:** Tuesday 21 to Thursday 23 May 2024

**Duration:** 9.30am - 4.00pm, each day

**Location: **K-D26 - BioScience

*You will receive a certificate of completion for the course.*