HEL-8002 Logistic Regression and Statistical Analysis of Survival Data - 3 stp

Two main topics are covered:

• Simple, multiple and stepwise logistic regression, matched case-control studies, and ordinal logistic regression
• Methods for analysis of survival data. Includes the Kaplan-Meier survival estimator, the log rank test, and Cox's Proportional Hazard regression model.

PhD students and students at the Student Research Programme, or holders of a Norwegian master´s degree of five years or 3+ 2 years (or equivalent) may be admitted. External PhD students and students at other Student Research Programmes, must upload a document from their university stating that they are registered students.

Admission recommendations:

Introductory course in medical statistics. It is recommended that students who are planning to take HEL-8024 complete it before taking this course.

Having attended the course and completed the exam the students will obtain the following learning outcomes:

Knowledge and understanding:

• Know how to specify a logistic regression model and a Cox proportional hazard regression model.
• Understand the difference between binary and ordinal logistic regression models.
• Understand when it is proper to use a logistic regression model.
• Understand when it is proper to use analysis of survival data.
• Interpret results from logistic regression models and analysis of survival data (Kaplan-Meier survival estimate, Cox regression models)

Skills:

• Be able to use a statistical package to analyse data using logistic regression models and models for the analysis of survival data (Kaplan-Meier survival function, log rank test, and Cox proportional hazard regression model).
• Identify different types of explanatory variables and correctly implement them in a logistic or Cox regression model.
• Be able to test interaction and assess confounding in logistic and Cox regression models.
• Evaluate the model assumptions

General Competence:

• Evaluate results from publications in medical journals where logistic models or Cox regression models are applied.
• Critically assess the validity of its use.