{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Week 4 Lecture Slides (1)

# Week 4 Lecture Slides (1) - Actuarial Statistics Week 4 The...

This preview shows pages 1–8. Sign up to view the full content.

Actuarial Statistics – Week 4: The Cox Regression Model ACTL3001 Actuarial Statistics Michael Sherris 1 c University of New South Wales (2014) School of Risk and Actuarial Studies, Australian School of Business ARC Centre of Excellence in Population Ageing Research [email protected] Week 4: The Cox regression model 1 Slides developed by previous LICs including Benjamin Avanzi 1/45

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

View Full Document
Actuarial Statistics – Week 4: The Cox Regression Model 1 Introduction 2 Main assumptions 3 On the proportionality of hazard rates 4 Estimation of the regression parameters β 5 Hypothesis tests on the β ’s 6 Estimation of the full survival function 7 Diagnostics for the Cox regression model 2/45
Actuarial Statistics – Week 4: The Cox Regression Model Introduction 1 Introduction 2 Main assumptions 3 On the proportionality of hazard rates 4 Estimation of the regression parameters β 5 Hypothesis tests on the β ’s 6 Estimation of the full survival function 7 Diagnostics for the Cox regression model 2/45

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

View Full Document
Actuarial Statistics – Week 4: The Cox Regression Model Introduction Why a regression model? Central question: How can we model separately different factors that are likely to impact the observed event, so that we can isolate their individual effects? Heterogeneity: lives with very different characteristics (eg males and females, smokers and non-smokers) have different level of mortality. In other words, different factors (covariates) may have different effects on the risk. One method is to construct a model including the effects of the covariates on survival directly: a regression model. The most widely used regression model is the proportional hazards model (the Cox model) 3/45
Actuarial Statistics – Week 4: The Cox Regression Model Introduction Covariates In many survival analysis problems, covariates are of the following types: Demographic / Societal (eg age, gender, education) Behavioral (eg smoking, physical activity level, alcohol) Physiological (eg blood pressure, heart rate) Covariates can be continuous measurements (weight) discrete measurements (age last birthday) indicators (1 for smoking, 0 for non-smoking) qualitative indicators (5 severe disease to 0 no symptoms) see K&M for a discussion of how to ‘code’ variables/factors 4/45

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

View Full Document
Actuarial Statistics – Week 4: The Cox Regression Model Introduction Notation For the i th life we will denote the covariates ( risk factors ) by a 1 × p vector Z i = ( z i 1 , z i 2 , . . . , z ip ) Example: Consider the covariate vector Z i = (sex, age, weight, symptoms) . If the 3rd life is a 68 year old male, weighing 74kg, with mild symptoms of the condition under investigation (graded as 1 on a scale of 0 to 5), then we have Z 3 = (0 , 68 , 74 , 1) . 5/45
Actuarial Statistics – Week 4: The Cox Regression Model Main assumptions 1 Introduction 2 Main assumptions 3 On the proportionality of hazard rates 4 Estimation of the regression parameters β 5 Hypothesis tests on the β ’s 6 Estimation of the full survival function 7 Diagnostics for the Cox regression model 5/45

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 52

Week 4 Lecture Slides (1) - Actuarial Statistics Week 4 The...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online