Multiple Regression Analysis in Public Health

Johns Hopkins University via Coursera

Coursera based on 308 ratings

Likes

Overview

Multiple Regression Analysis in Public Health is an advanced, application-focused course that teaches learners how to use multiple regression techniques to explore and quantify relationships between multiple variables in public health research. Aimed at students, health professionals, and researchers with basic statistical knowledge, the course focuses on using regression models to draw meaningful insights from complex health data. The course begins with a review of linear regression fundamentals before progressing to multiple regression models. Learners will understand how to build and...

Syllabus

An Overview of Multiple Regression for Estimation, Adjustment, and Basic Prediction, and Multiple Linear Regression

Within this module, an overview of multiple regression will be provided. Additionally, examples and applications will be examined. A practice quiz is provided to test your knowledge before completing the graded quiz.

Multiple Logistic Regression

Module two covers examples of multiple logistic regression, basics of model estimates, and a discussion of effect modification. In addition to lectures, you will also be completing a practice quiz and graded quiz.

Multiple Cox Regression

The last module for this class focuses on multiple Cox regression, the Linearity assumption, examples, and applications. You will complete a practice quiz, graded quiz, and project.

Course Project

During this module, you get the chance to demonstrate what you've learned by putting yourself in the shoes of biostatistical consultant on two different studies, one about self-administration of injectable contraception and one about medical appointment scheduling in Brazil. The two research teams have asked you to them interpret previously published results in order to inform the planning of their own studies. If you've already taken other courses in this specialization, then this scenario will be familiar.