1018Gage_Survival AnalysisB - October19,2004...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Introduction to Survival Analysis October 19, 2004 Brian F. Gage, MD, MSc  with thanks to Bing Ho, MD, MPH Division of General Medical Sciences
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Presentation goals Survival analysis compared w/ other regression  techniques What is survival analysis When to use survival analysis Univariate method: Kaplan-Meier curves Multivariate methods: Cox-proportional hazards model Parametric models Assessment of adequacy of analysis Examples
Background image of page 2
Regression vs. Survival Analysis Technique Predictor Variables Outcome Variable Censoring permitted? Linear Regression Categorical or continuous Normally distributed No Logistic Regression Categorical or continuous Binary (except in polytomous log. regression) No Survival Analyses Time and categorical or continuous Binary Yes
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Regression vs. Survival Analysis Technique Mathematical model Yields Linear Regression Y=B 1 X + B o (linear) Linear changes Logistic Regression Ln(P/1-P)=B 1 X+B o (sigmoidal prob.) Odds ratios Survival Analyses h(t) = h o (t)exp( B 1 X+B o) Hazard rates
Background image of page 4
What is survival analysis? Model  time to failure  or  time to event Unlike linear regression, survival analysis has a  dichotomous (binary) outcome Unlike logistic regression, survival analysis analyzes  the time to an event  Why is that important? Able to account for censoring Can  compare survival  between 2+ groups Assess  relationship between covariates and  survival time
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Importance of censored data Why is censored data important? What is the key assumption of censoring?
Background image of page 6
Types of censoring Subject does not  experience event of  interest Incomplete follow-up Lost to follow-up Withdraws from study Dies (if not being studied) Left  or  right  censored
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
When to use survival analysis Examples Time to death or clinical endpoint Time in remission after treatment of disease Recidivism rate after addiction treatment When one believes that 1+ explanatory variable(s)  explains the differences in time to an event Especially when follow-up is incomplete or  variable
Background image of page 8
Relationship between survivor function  and hazard function Survivor function, S(t) defines the probability of  surviving longer than time  t this is what the Kaplan-Meier curves show. Hazard function is the derivative of the survivor 
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 08/26/2010 for the course MEDICAL md0897 taught by Professor Prof during the Spring '04 term at Medical Careers Institute.

Page1 / 33

1018Gage_Survival AnalysisB - October19,2004...

This preview shows document pages 1 - 10. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online