Survival Analysis in R for Public Health

Go to Course: https://www.coursera.org/learn/survival-analysis-r-public-health

Introduction

**Course Review: Survival Analysis in R for Public Health** **Overview** If you have a passion for public health and are keen to enhance your statistical analysis skills, Coursera's "Survival Analysis in R for Public Health" is a must-take course. This course stands as a continuation of foundational statistical concepts, building upon earlier essential courses in statistical thinking, correlation, linear regression, and logistic regression. Here, you will delve into the realm of survival analysis, an integral aspect when dealing with time-to-event data in health research. The course is situated in the context of public health, elucidating critical concepts with real-world applications. You will familiarize yourself with specialized terms, particularly those that may seem familiar but hold unique meanings within this analytical framework, such as "hazard" and "censoring." The inclusion of R, a popular open-source statistical software, allows learners to execute their newfound knowledge hands-on, using real datasets to conduct survival analyses from scratch. **Syllabus Breakdown** The syllabus is thoughtfully structured into four key areas, allowing learners to develop a comprehensive understanding and practical skills in survival analysis: 1. **The Kaplan-Meier Plot**: The introductory week begins by defining survival analysis, outlining its applications, and exploring the Kaplan-Meier plot—a crucial descriptive method in survival analysis. You will learn to interpret this plot effectively and understand the log-rank test for comparing survival times among different patient groups, such as those receiving various treatments. Key concepts, notably the significance of censoring (where information is incomplete for some subjects), are thoroughly discussed. 2. **The Cox Model**: As the course progresses, you will dive into Cox proportional hazards regression modeling—an essential method known for incorporating multiple predictors of survival. You will gain insights into hazards and the risk set while applying this method to simulated patient data, particularly focusing on individuals hospitalized with heart failure. The course highlights potential pitfalls with missing data and categorical variables, equipping you with valuable knowledge on addressing these challenges. 3. **The Multiple Cox Model**: The focus shifts toward extending the simple Cox model into a more complex multiple Cox model. Prior to fitting the model, you will perform descriptive statistics on your primary variables to prepare for analysis. You will encounter real-life public health data scenarios, offering practical solutions to common issues faced during regression analysis. 4. **The Proportionality Assumption**: In the final section, the course emphasizes the assessment of model fit and the testing of key assumptions intrinsic to Cox regression, particularly exploring the proportional hazards assumption. You will learn to analyze various types of residuals and apply a multiple Cox regression model, making critical decisions regarding predictor inclusion—a persistent challenge within regression modeling. **Recommendations** I wholeheartedly recommend "Survival Analysis in R for Public Health" for anyone engaged in public health research or related fields. The course is impeccably structured, gradually guiding learners from fundamental concepts to more advanced analytical techniques. The hands-on approach using R not only fortifies theoretical understanding but also cultivates practical skills applicable in real-world scenarios. This course is ideal for graduate students, public health professionals, or anyone interested in enhancing their statistical acumen with a specific focus on survival analysis. Moreover, the course provides detailed instructions and ample opportunities to practice, ensuring a thorough grasp of the material. In conclusion, whether you're looking to elevate your analytical skills or deepen your understanding of survival analysis in the context of public health, this course is a valuable resource to consider. With its comprehensive content, engaging format, and practical applicability, it stands as an excellent choice for your educational journey in statistics.

Syllabus

The Kaplan-Meier Plot

What is survival analysis? You’ll see what it is, when to use it and how to run and interpret the most common descriptive survival analysis method, the Kaplan-Meier plot and its associated log-rank test for comparing the survival of two or more patient groups, e.g. those on different treatments. You’ll learn about the key concept of censoring.

This week you’ll get to know the most commonly used survival analysis method for incorporating not just one but multiple predictors of survival: Cox proportional hazards regression modelling. You’ll learn about the key concepts of hazards and the risk set. From now and until the end of this course, there’ll be plenty of chance to run Cox models on data simulated from real patient-level records for people admitted to hospital with heart failure. You’ll see why missing data and categorical variables can cause problems in regression models such as Cox.

You’ll extend the simple Cox model to the multiple Cox model. As preparation, you’ll run the essential descriptive statistics on your main variables. Then you’ll see what can happen with real-life public health data and learn some simple tricks to fix the problem.

In this final part of the course, you’ll learn how to assess the fit of the model and test the validity of the main assumptions involved in Cox regression such as proportional hazards. This will cover three types of residuals. Lastly, you’ll get to practise fitting a multiple Cox regression model and will have to decide which predictors to include and which to drop, a ubiquitous challenge for people fitting any type of regression model.