Analysis of Time-to-Event Data: Chapter 4 - Parametric regression models
|
|
- Anna Tate
- 5 years ago
- Views:
Transcription
1 Analysis of Time-to-Event Data: Chapter 4 - Parametric regression models Steffen Unkel Department of Medical Statistics University Medical Center Göttingen, Germany Winter term 2018/19 1/25
2 Right censored time-to-event data with covariates Suppose the following data are available: D t n = {(t i, δ i, x i ), i = 1,..., n}, where t i observed survival time for the ith individual, δ i : censoring indicator, x i = (x i1,..., x ip ) : vector of covariates. Non-informative random censoring with t i = min(t i, C i ) and δ i = I (T i C i ), where I ( ) denotes the indicator function. The covariates are assumed to be independent of time t. Winter term 2018/19 2/25
3 Regression models for time-to-event data How can we study the effect of a number of covariates on the survival experience in a manner similar to other regression models? There may be settings in which the distribution of survival time has a known parametric form. A fully parametric regression model accomplishes two goals simultaneously: 1 it describes the basic underlying distribution of survival time (error component), and 2 it characterizes how the the distribution changes as a function of the covariates (systematic component). Winter term 2018/19 3/25
4 Proportional hazards assumption Suppose that patients are randomised to receive either a standard treatment or a new treatment. Let h S (t) (h N (t)) be the hazard of death at time t for patients on the standard treatment (new treatment). Proportional hazards assumption: h N (t) = ψh S (t), where ψ is a constant, known as the hazard ratio. If ψ < 1 (ψ > 1), the hazard of death at t is smaller (greater) for an individual on the new drug, relative to an individual on the standard treatment. Winter term 2018/19 4/25
5 General proportional hazards model Let h 0 (t) be the hazard function for an individual for whom x = 0, known as the baseline hazard function. The hazard function for the ith individual can then be written as h i (t) = exp(x i θ)h 0 (t), where θ = (θ 1,..., θ p ) is the vector of coefficients of the explanatory variables x 1,..., x p. Linear model for the logarithm of the hazards ratio: ( ) hi (t) ln = x i θ. h 0 (t) Winter term 2018/19 5/25
6 Parametric proportional hazards models In semiparametric proportional hazards models, the form of h 0 (t) is unspecified. In parametric models a specific probability distribution is assumed for the survival times, and this imposes a particular parametric form on h 0 (t). However, relatively few probability distributions can be used with parametric proportional hazards models. Moreover, distributions that are available such as the Weibull and Gompertz distribution lead to hazard functions that increase or decrease monotonically. Winter term 2018/19 6/25
7 Parametric regression structure The distribution of T as a function of covariates x is characterized via the equation T = exp(x β) exp(σɛ), where β = (β 0, β 1,..., β p ) is vector of regression coefficients, ɛ is the error component and σ is a scale parameter for the distribution of ɛ. Log-linear form of the model: ln(t ) = x β + σɛ. Survival time models that can be linearized by taking logs are called accelerated failure time (AFT) models. Winter term 2018/19 7/25
8 Accelerated failure time assumption Let S S (t) and S NS (t) denote the survival functions of smokers and non-smokers, respectively. AFT assumption: S NS (t) = S S (γt), where γ > 0 is a constant named acceleration factor. The AFT assumption can also be expressed as γt NS = T S, where T NS is a random variable representing the survival time for nonsmokers and T S is the analogous one for smokers. Winter term 2018/19 8/25
9 cceleration factor he acceleration factor is a ratio of time-quantiles corresponding to Illustration 268 the 7. y fixed value of S(t). acceleration Parametric factor Survival Models S(t) γ = 2 distance to G = 1 distance to G = 2 G = 1 G = 2 Survival curves for Group 1 (G = 1) and Group 2 (G = 2) Horizontal lines are twice as long to G = 2Winter compared term 2018/19 to 9/25 G = 1 because t This idea is gra the survival cur 2(G= 2) show S(t), the distan S(t) axis to the the distance to tice the median and 75th percen models, this rat stant for all fixe Figure: Acceleration factor γ as ratio of time-quantiles corresponding to any fixed value of S(t). For γ > 1 (γ < 1): exposure benefits (is harmful to) survival for Group G = 2.
10 Acceleration factor in a regression framework The acceleration factor allows to evaluate the effect of predictor variables on the survival time. AFT model: Y = ln(t ) = x β + σɛ T = exp(x β) exp(σɛ), }{{} T 0 where T 0 denotes the baseline survival time. Often, the baseline survival time is defined as T 0 = exp(β 0 + σɛ). Let S T0 denote the baseline survival function, then it holds that S T (t) = S T0 (t exp( x β)). Winter term 2018/19 10/25
11 Genesis of AFT models Various choices for the distribution of ɛ can be made: Distribution of ɛ Standard Gumbel (minimum) with σ = 1 Standard Gumbel (minimum) with σ 1 Standard logistic Standard normal Distribution of T Exponential Weibull Log-logistic Log-normal Note that the Gumbel distribution is also referred to as the extreme value type I distribution. Winter term 2018/19 11/25
12 Exponential regression model AFT model with σ = 1: Y = ln(t ) = x β + ɛ, where ɛ follows the standard Gumbel (minimum) distribution, denoted as G(0, 1), with density f ɛ (ɛ) = exp(ɛ exp(ɛ)) for ɛ R. Density of survival time T : f T (t) = exp( x β) exp( (t exp( x β))). Set λ := exp( x β), then f T (t) = λ exp( λt) T E(λ). Winter term 2018/19 12/25
13 Weibull regression model AFT model with σ 1: ln(t ) = x β + σɛ, where ɛ follows the standard Gumbel (minimum) distribution. T WB(α, λ). The Weibull regression model is an AFT model that has proportional hazards. The correspondence between the AFT representation and the proportional hazards representation is such that ( ) λ = exp x β, α = 1/σ, θ j = β j /σ (j = 1,..., p). σ Winter term 2018/19 13/25
14 Log-logistic regression model AFT model: ln(t ) = x β + σɛ, where ɛ follows the standard logistic distribution with density f ɛ (ɛ) = exp(ɛ)/(1 + exp(ɛ)) 2 for ɛ R. T has a log-logistic distribution with parameters α and γ. In the log-logistic model, the regression coefficients can be expressed in such a way that they can be interpreted as odds ratios. The log-logistic regression model is an AFT model that has proportional odds. Winter term 2018/19 14/25
15 Log-normal regression model AFT model: ln(t ) = x β + σɛ, ɛ N (0, 1). Y = ln(t ) N (x β, σ 2 ) with ( ) y x h Y (y) = 1 φ β σ ( ), σ y x 1 Φ β σ where φ( ) and Φ( ) denote the pdf and cdf of the standard normal distribution, respectively. T LN (x β, σ 2 ) with h T (t) = 1 t h Y (ln(t)). Winter term 2018/19 15/25
16 Log-Likelihood Likelihood: n n L(θ Dn) t = [f i (t i θ)] δ i [S i (t i θ)] 1 δ i = [h i (t i θ)] δ i S i (t i θ), where θ = (β, σ) is the vector of unknown parameters. Log-likelihood: l(θ D t n) = = n [δ i ln(f i (t i θ)) + (1 δ i ) ln(s i (t i θ))] n [δ i ln(h i (t i θ)) + ln(s i (t i θ))]. Winter term 2018/19 16/25
17 Log-Likelihood (2) Let ɛ i (t i ) := (ln(t i ) x i β)/σ. Then S i (t i ) = S ɛ (ɛ i (t i )), f i (t i ) = f ɛ(ɛ i (t i )), h i (t i ) = 1 h ɛ (ɛ i (t i )). σt i σt i The log-likelihood can then be written as n l(β, σ Dn) t = [ δ i ln(σt i ) + δ i ln(f ɛ(ɛ i (t i ))) + (1 δ i ) ln(s ɛ(ɛ i (t i )))] = c 1 + n [ δ i ln(σ) + δ i ln(f ɛ(ɛ i (t i ))) + (1 δ i ) ln(s ɛ(ɛ i (t i )))]. or alternatively n l(β, σ Dn) t = [ δ i ln(σt i ) + δ i ln(h ɛ(ɛ i (t i ))) + ln(s ɛ(ɛ i (t i )))] = c 1 + n [ δ i ln(σ) + δ i ln(h ɛ(ɛ i (t i ))) + ln(s ɛ(ɛ i (t i )))]. Winter term 2018/19 17/25
18 Log-Likelihood of the transformed data For the transformations y i = min{ln(t i ), ln(c i )} we denote the data as D y n = {(y i, δ i, x i ), i = 1,..., n}. With θ = (β, σ) and ɛ i (y i ) = (y i x i β)/σ it holds that S i (y i ) = S ɛ (ɛ i (y i )), f i (y i ) = f ɛ(ɛ i (y i )), h i (y i ) = 1 σ σ h ɛ(ɛ i (y i )). Log-likelihood for Dn y : n l(β, σ Dn y ) = [ δ i ln(σ) + δ i ln(f ɛ (ɛ i (y i ))) + (1 δ i ) ln(s ɛ (ɛ i (y i )))] = n [ δ i ln(σ) + δ i ln(h ɛ (ɛ i (y i ))) + ln(s ɛ (ɛ i (y i )))]. It follows that l(β, σ D y n ) + c 2 = l(β, σ D t n). Winter term 2018/19 18/25
19 Score function The first derivatives of the log-likelihood with respect to the unknown parameters are s β (β, σ) = s σ (β, σ) = l(β, σ) β l(β, σ) σ = 1 σ = 1 σ n a i x i n (δ i + ɛ i a i ) with a i = δ i d ln h ɛ (ɛ i (y i )) dɛ h ɛ (ɛ i (y i )). Winter term 2018/19 19/25
20 Hesse matrix The matrix of second derivatives has entries with 2 l(β, σ) β β = 1 σ 2 2 l(β, σ) β σ 2 l(β, σ) σ 2 = 1 σ 2 n b i x i x i = 1 n σ 2 [a i + ɛ i (y i )b i ]x i n [ δi + 2ɛ i (y i )a i + (ɛ i (y i )) 2 ] b i b i = da i dɛ = δ d 2 ln h ɛ (ɛ i (y i )) i dɛ 2 dh ɛ(ɛ i (y i )) dɛ. Winter term 2018/19 20/25
21 Confidence intervals The inverse of the observed Fisher information matrix provides estimators of the variances and covariances: Ĉov(ˆβ) = I(ˆβ) 1. Typically, software packages provide estimates of the standard errors of each of the model coefficients, which are the square roots of the elements on the main diagonal of Ĉov(ˆβ). The endpoints of a 100(1 α)% confidence interval for the jth coefficient are ˆβ j ± z 1 α/2 s.e.( ˆβ j ), where s.e.( ˆβ j ) denotes the standard error of the estimator of the coefficient j. Winter term 2018/19 21/25
22 Testing of linear hypotheses To test a linear relationship among x 1,..., x p is equivalent to testing the null hypothesis that there is a linear relationship among β 1,..., β p. The null hypothesis can be written in general as H 0 : Cβ = d, where C is a matrix of constants for the linear hypothesis and d is a known column vector of constants. Winter term 2018/19 22/25
23 Likelihood ratio test The likelihood ratio test statistic is defined as where Q = 2[ln L(ˆβ) ln L( β)], ˆβ = arg max l(β) β = arg max Cβ=d l(β) are the ML estimators obtained without and with restrictions under H 0 imposed on the parameters, respectively. It holds that Q a χ 2 (rank(c)). Winter term 2018/19 23/25
24 Wald test The Wald statistic is defined as W = (Cˆβ d) [CĈov(ˆβ)C ] 1 (Cˆβ d), where CĈov(ˆβ)C is the covariance matrix of Cˆβ. The Wald statistic only needs the ML estimator for the unrestrictive model. It holds that W a χ 2 (rank(c)). Winter term 2018/19 24/25
25 Score test The score statistic is defined as S = s( β) I( β) 1 s( β), where s( β) is the score vector for β. The score statistic only needs the ML estimator for the restrictive model. It holds that S a χ 2 (rank(c)). Winter term 2018/19 25/25
STAT 6350 Analysis of Lifetime Data. Failure-time Regression Analysis
STAT 6350 Analysis of Lifetime Data Failure-time Regression Analysis Explanatory Variables for Failure Times Usually explanatory variables explain/predict why some units fail quickly and some units survive
More informationAnalysis of Time-to-Event Data: Chapter 6 - Regression diagnostics
Analysis of Time-to-Event Data: Chapter 6 - Regression diagnostics Steffen Unkel Department of Medical Statistics University Medical Center Göttingen, Germany Winter term 2018/19 1/25 Residuals for the
More informationSemiparametric Regression
Semiparametric Regression Patrick Breheny October 22 Patrick Breheny Survival Data Analysis (BIOS 7210) 1/23 Introduction Over the past few weeks, we ve introduced a variety of regression models under
More informationOther Survival Models. (1) Non-PH models. We briefly discussed the non-proportional hazards (non-ph) model
Other Survival Models (1) Non-PH models We briefly discussed the non-proportional hazards (non-ph) model λ(t Z) = λ 0 (t) exp{β(t) Z}, where β(t) can be estimated by: piecewise constants (recall how);
More informationMAS3301 / MAS8311 Biostatistics Part II: Survival
MAS3301 / MAS8311 Biostatistics Part II: Survival M. Farrow School of Mathematics and Statistics Newcastle University Semester 2, 2009-10 1 13 The Cox proportional hazards model 13.1 Introduction In the
More informationSTAT 331. Accelerated Failure Time Models. Previously, we have focused on multiplicative intensity models, where
STAT 331 Accelerated Failure Time Models Previously, we have focused on multiplicative intensity models, where h t z) = h 0 t) g z). These can also be expressed as H t z) = H 0 t) g z) or S t z) = e Ht
More informationSurvival Analysis Math 434 Fall 2011
Survival Analysis Math 434 Fall 2011 Part IV: Chap. 8,9.2,9.3,11: Semiparametric Proportional Hazards Regression Jimin Ding Math Dept. www.math.wustl.edu/ jmding/math434/fall09/index.html Basic Model Setup
More informationQuantile Regression for Residual Life and Empirical Likelihood
Quantile Regression for Residual Life and Empirical Likelihood Mai Zhou email: mai@ms.uky.edu Department of Statistics, University of Kentucky, Lexington, KY 40506-0027, USA Jong-Hyeon Jeong email: jeong@nsabp.pitt.edu
More informationSurvival Regression Models
Survival Regression Models David M. Rocke May 18, 2017 David M. Rocke Survival Regression Models May 18, 2017 1 / 32 Background on the Proportional Hazards Model The exponential distribution has constant
More informationChapter 17. Failure-Time Regression Analysis. William Q. Meeker and Luis A. Escobar Iowa State University and Louisiana State University
Chapter 17 Failure-Time Regression Analysis William Q. Meeker and Luis A. Escobar Iowa State University and Louisiana State University Copyright 1998-2008 W. Q. Meeker and L. A. Escobar. Based on the authors
More informationβ j = coefficient of x j in the model; β = ( β1, β2,
Regression Modeling of Survival Time Data Why regression models? Groups similar except for the treatment under study use the nonparametric methods discussed earlier. Groups differ in variables (covariates)
More informationPower and Sample Size Calculations with the Additive Hazards Model
Journal of Data Science 10(2012), 143-155 Power and Sample Size Calculations with the Additive Hazards Model Ling Chen, Chengjie Xiong, J. Philip Miller and Feng Gao Washington University School of Medicine
More informationChapter 2 Inference on Mean Residual Life-Overview
Chapter 2 Inference on Mean Residual Life-Overview Statistical inference based on the remaining lifetimes would be intuitively more appealing than the popular hazard function defined as the risk of immediate
More informationMAS3301 / MAS8311 Biostatistics Part II: Survival
MAS330 / MAS83 Biostatistics Part II: Survival M. Farrow School of Mathematics and Statistics Newcastle University Semester 2, 2009-0 8 Parametric models 8. Introduction In the last few sections (the KM
More informationBeyond GLM and likelihood
Stat 6620: Applied Linear Models Department of Statistics Western Michigan University Statistics curriculum Core knowledge (modeling and estimation) Math stat 1 (probability, distributions, convergence
More information5. Parametric Regression Model
5. Parametric Regression Model The Accelerated Failure Time (AFT) Model Denote by S (t) and S 2 (t) the survival functions of two populations. The AFT model says that there is a constant c > 0 such that
More informationLinear models and their mathematical foundations: Simple linear regression
Linear models and their mathematical foundations: Simple linear regression Steffen Unkel Department of Medical Statistics University Medical Center Göttingen, Germany Winter term 2018/19 1/21 Introduction
More informationAccelerated Failure Time Models
Accelerated Failure Time Models Patrick Breheny October 12 Patrick Breheny University of Iowa Survival Data Analysis (BIOS 7210) 1 / 29 The AFT model framework Last time, we introduced the Weibull distribution
More informationProportional hazards regression
Proportional hazards regression Patrick Breheny October 8 Patrick Breheny Survival Data Analysis (BIOS 7210) 1/28 Introduction The model Solving for the MLE Inference Today we will begin discussing regression
More informationSurvival Analysis. Stat 526. April 13, 2018
Survival Analysis Stat 526 April 13, 2018 1 Functions of Survival Time Let T be the survival time for a subject Then P [T < 0] = 0 and T is a continuous random variable The Survival function is defined
More informationLecture 22 Survival Analysis: An Introduction
University of Illinois Department of Economics Spring 2017 Econ 574 Roger Koenker Lecture 22 Survival Analysis: An Introduction There is considerable interest among economists in models of durations, which
More informationGeneralized Linear Models
Generalized Linear Models Lecture 3. Hypothesis testing. Goodness of Fit. Model diagnostics GLM (Spring, 2018) Lecture 3 1 / 34 Models Let M(X r ) be a model with design matrix X r (with r columns) r n
More informationST495: Survival Analysis: Maximum likelihood
ST495: Survival Analysis: Maximum likelihood Eric B. Laber Department of Statistics, North Carolina State University February 11, 2014 Everything is deception: seeking the minimum of illusion, keeping
More informationLogistic regression model for survival time analysis using time-varying coefficients
Logistic regression model for survival time analysis using time-varying coefficients Accepted in American Journal of Mathematical and Management Sciences, 2016 Kenichi SATOH ksatoh@hiroshima-u.ac.jp Research
More informationChapter 4 Regression Models
23.August 2010 Chapter 4 Regression Models The target variable T denotes failure time We let x = (x (1),..., x (m) ) represent a vector of available covariates. Also called regression variables, regressors,
More informationSimulation-based robust IV inference for lifetime data
Simulation-based robust IV inference for lifetime data Anand Acharya 1 Lynda Khalaf 1 Marcel Voia 1 Myra Yazbeck 2 David Wensley 3 1 Department of Economics Carleton University 2 Department of Economics
More informationLecture 8. Poisson models for counts
Lecture 8. Poisson models for counts Jesper Rydén Department of Mathematics, Uppsala University jesper.ryden@math.uu.se Statistical Risk Analysis Spring 2014 Absolute risks The failure intensity λ(t) describes
More informationTMA 4275 Lifetime Analysis June 2004 Solution
TMA 4275 Lifetime Analysis June 2004 Solution Problem 1 a) Observation of the outcome is censored, if the time of the outcome is not known exactly and only the last time when it was observed being intact,
More informationPENALIZED LIKELIHOOD PARAMETER ESTIMATION FOR ADDITIVE HAZARD MODELS WITH INTERVAL CENSORED DATA
PENALIZED LIKELIHOOD PARAMETER ESTIMATION FOR ADDITIVE HAZARD MODELS WITH INTERVAL CENSORED DATA Kasun Rathnayake ; A/Prof Jun Ma Department of Statistics Faculty of Science and Engineering Macquarie University
More informationAnalysis of Time-to-Event Data: Chapter 2 - Nonparametric estimation of functions of survival time
Analysis of Time-to-Event Data: Chapter 2 - Nonparametric estimation of functions of survival time Steffen Unkel Department of Medical Statistics University Medical Center Göttingen, Germany Winter term
More informationCox s proportional hazards model and Cox s partial likelihood
Cox s proportional hazards model and Cox s partial likelihood Rasmus Waagepetersen October 12, 2018 1 / 27 Non-parametric vs. parametric Suppose we want to estimate unknown function, e.g. survival function.
More informationLinear Regression Models P8111
Linear Regression Models P8111 Lecture 25 Jeff Goldsmith April 26, 2016 1 of 37 Today s Lecture Logistic regression / GLMs Model framework Interpretation Estimation 2 of 37 Linear regression Course started
More informationSurvival Analysis. Lu Tian and Richard Olshen Stanford University
1 Survival Analysis Lu Tian and Richard Olshen Stanford University 2 Survival Time/ Failure Time/Event Time We will introduce various statistical methods for analyzing survival outcomes What is the survival
More informationFrailty Modeling for clustered survival data: a simulation study
Frailty Modeling for clustered survival data: a simulation study IAA Oslo 2015 Souad ROMDHANE LaREMFiQ - IHEC University of Sousse (Tunisia) souad_romdhane@yahoo.fr Lotfi BELKACEM LaREMFiQ - IHEC University
More informationApproximation of Survival Function by Taylor Series for General Partly Interval Censored Data
Malaysian Journal of Mathematical Sciences 11(3): 33 315 (217) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES Journal homepage: http://einspem.upm.edu.my/journal Approximation of Survival Function by Taylor
More informationIntroduction to Statistical Analysis
Introduction to Statistical Analysis Changyu Shen Richard A. and Susan F. Smith Center for Outcomes Research in Cardiology Beth Israel Deaconess Medical Center Harvard Medical School Objectives Descriptive
More informationIntroduction to General and Generalized Linear Models
Introduction to General and Generalized Linear Models Generalized Linear Models - part III Henrik Madsen Poul Thyregod Informatics and Mathematical Modelling Technical University of Denmark DK-2800 Kgs.
More information9 Generalized Linear Models
9 Generalized Linear Models The Generalized Linear Model (GLM) is a model which has been built to include a wide range of different models you already know, e.g. ANOVA and multiple linear regression models
More information8. Parametric models in survival analysis General accelerated failure time models for parametric regression
8. Parametric models in survival analysis 8.1. General accelerated failure time models for parametric regression The accelerated failure time model Let T be the time to event and x be a vector of covariates.
More informationBayesian Nonparametric Accelerated Failure Time Models for Analyzing Heterogeneous Treatment Effects
Bayesian Nonparametric Accelerated Failure Time Models for Analyzing Heterogeneous Treatment Effects Nicholas C. Henderson Thomas A. Louis Gary Rosner Ravi Varadhan Johns Hopkins University September 28,
More informationChapter 4. Parametric Approach. 4.1 Introduction
Chapter 4 Parametric Approach 4.1 Introduction The missing data problem is already a classical problem that has not been yet solved satisfactorily. This problem includes those situations where the dependent
More informationSTATISTICAL INFERENCE IN ACCELERATED LIFE TESTING WITH GEOMETRIC PROCESS MODEL. A Thesis. Presented to the. Faculty of. San Diego State University
STATISTICAL INFERENCE IN ACCELERATED LIFE TESTING WITH GEOMETRIC PROCESS MODEL A Thesis Presented to the Faculty of San Diego State University In Partial Fulfillment of the Requirements for the Degree
More informationSample Size Determination
Sample Size Determination 018 The number of subjects in a clinical study should always be large enough to provide a reliable answer to the question(s addressed. The sample size is usually determined by
More informationVariable Selection in Competing Risks Using the L1-Penalized Cox Model
Virginia Commonwealth University VCU Scholars Compass Theses and Dissertations Graduate School 2008 Variable Selection in Competing Risks Using the L1-Penalized Cox Model XiangRong Kong Virginia Commonwealth
More informationST5212: Survival Analysis
ST51: Survival Analysis 8/9: Semester II Tutorial 1. A model for lifetimes, with a bathtub-shaped hazard rate, is the exponential power distribution with survival fumction S(x) =exp{1 exp[(λx) α ]}. (a)
More informationUNIVERSITY OF CALIFORNIA, SAN DIEGO
UNIVERSITY OF CALIFORNIA, SAN DIEGO Estimation of the primary hazard ratio in the presence of a secondary covariate with non-proportional hazards An undergraduate honors thesis submitted to the Department
More informationA Bivariate Weibull Regression Model
c Heldermann Verlag Economic Quality Control ISSN 0940-5151 Vol 20 (2005), No. 1, 1 A Bivariate Weibull Regression Model David D. Hanagal Abstract: In this paper, we propose a new bivariate Weibull regression
More informationUniversity of California, Berkeley
University of California, Berkeley U.C. Berkeley Division of Biostatistics Working Paper Series Year 24 Paper 153 A Note on Empirical Likelihood Inference of Residual Life Regression Ying Qing Chen Yichuan
More informationModeling and Measuring Association for Ordinal Data
Modeling and Measuring Association for Ordinal Data A Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Science in
More informationAdvanced Quantitative Methods: maximum likelihood
Advanced Quantitative Methods: Maximum Likelihood University College Dublin 4 March 2014 1 2 3 4 5 6 Outline 1 2 3 4 5 6 of straight lines y = 1 2 x + 2 dy dx = 1 2 of curves y = x 2 4x + 5 of curves y
More informationST745: Survival Analysis: Cox-PH!
ST745: Survival Analysis: Cox-PH! Eric B. Laber Department of Statistics, North Carolina State University April 20, 2015 Rien n est plus dangereux qu une idee, quand on n a qu une idee. (Nothing is more
More informationSTAT 6350 Analysis of Lifetime Data. Probability Plotting
STAT 6350 Analysis of Lifetime Data Probability Plotting Purpose of Probability Plots Probability plots are an important tool for analyzing data and have been particular popular in the analysis of life
More informationAFT Models and Empirical Likelihood
AFT Models and Empirical Likelihood Mai Zhou Department of Statistics, University of Kentucky Collaborators: Gang Li (UCLA); A. Bathke; M. Kim (Kentucky) Accelerated Failure Time (AFT) models: Y = log(t
More informationBIOS 2083 Linear Models c Abdus S. Wahed
Chapter 5 206 Chapter 6 General Linear Model: Statistical Inference 6.1 Introduction So far we have discussed formulation of linear models (Chapter 1), estimability of parameters in a linear model (Chapter
More informationLogistic regression. 11 Nov Logistic regression (EPFL) Applied Statistics 11 Nov / 20
Logistic regression 11 Nov 2010 Logistic regression (EPFL) Applied Statistics 11 Nov 2010 1 / 20 Modeling overview Want to capture important features of the relationship between a (set of) variable(s)
More informationSTAT331. Cox s Proportional Hazards Model
STAT331 Cox s Proportional Hazards Model In this unit we introduce Cox s proportional hazards (Cox s PH) model, give a heuristic development of the partial likelihood function, and discuss adaptations
More informationBIAS OF MAXIMUM-LIKELIHOOD ESTIMATES IN LOGISTIC AND COX REGRESSION MODELS: A COMPARATIVE SIMULATION STUDY
BIAS OF MAXIMUM-LIKELIHOOD ESTIMATES IN LOGISTIC AND COX REGRESSION MODELS: A COMPARATIVE SIMULATION STUDY Ingo Langner 1, Ralf Bender 2, Rebecca Lenz-Tönjes 1, Helmut Küchenhoff 2, Maria Blettner 2 1
More informationADVANCED STATISTICAL ANALYSIS OF EPIDEMIOLOGICAL STUDIES. Cox s regression analysis Time dependent explanatory variables
ADVANCED STATISTICAL ANALYSIS OF EPIDEMIOLOGICAL STUDIES Cox s regression analysis Time dependent explanatory variables Henrik Ravn Bandim Health Project, Statens Serum Institut 4 November 2011 1 / 53
More informationStep-Stress Models and Associated Inference
Department of Mathematics & Statistics Indian Institute of Technology Kanpur August 19, 2014 Outline Accelerated Life Test 1 Accelerated Life Test 2 3 4 5 6 7 Outline Accelerated Life Test 1 Accelerated
More information22s:152 Applied Linear Regression. Example: Study on lead levels in children. Ch. 14 (sec. 1) and Ch. 15 (sec. 1 & 4): Logistic Regression
22s:52 Applied Linear Regression Ch. 4 (sec. and Ch. 5 (sec. & 4: Logistic Regression Logistic Regression When the response variable is a binary variable, such as 0 or live or die fail or succeed then
More informationIntroduction to Estimation Methods for Time Series models Lecture 2
Introduction to Estimation Methods for Time Series models Lecture 2 Fulvio Corsi SNS Pisa Fulvio Corsi Introduction to Estimation () Methods for Time Series models Lecture 2 SNS Pisa 1 / 21 Estimators:
More informationIntegrated likelihoods in survival models for highlystratified
Working Paper Series, N. 1, January 2014 Integrated likelihoods in survival models for highlystratified censored data Giuliana Cortese Department of Statistical Sciences University of Padua Italy Nicola
More information11 Survival Analysis and Empirical Likelihood
11 Survival Analysis and Empirical Likelihood The first paper of empirical likelihood is actually about confidence intervals with the Kaplan-Meier estimator (Thomas and Grunkmeier 1979), i.e. deals with
More informationModern Methods of Statistical Learning sf2935 Lecture 5: Logistic Regression T.K
Lecture 5: Logistic Regression T.K. 10.11.2016 Overview of the Lecture Your Learning Outcomes Discriminative v.s. Generative Odds, Odds Ratio, Logit function, Logistic function Logistic regression definition
More informationUNIVERSITÄT POTSDAM Institut für Mathematik
UNIVERSITÄT POTSDAM Institut für Mathematik Testing the Acceleration Function in Life Time Models Hannelore Liero Matthias Liero Mathematische Statistik und Wahrscheinlichkeitstheorie Universität Potsdam
More informationPart III. Hypothesis Testing. III.1. Log-rank Test for Right-censored Failure Time Data
1 Part III. Hypothesis Testing III.1. Log-rank Test for Right-censored Failure Time Data Consider a survival study consisting of n independent subjects from p different populations with survival functions
More informationLikelihood Construction, Inference for Parametric Survival Distributions
Week 1 Likelihood Construction, Inference for Parametric Survival Distributions In this section we obtain the likelihood function for noninformatively rightcensored survival data and indicate how to make
More informationStatistical Inference on Constant Stress Accelerated Life Tests Under Generalized Gamma Lifetime Distributions
Int. Statistical Inst.: Proc. 58th World Statistical Congress, 2011, Dublin (Session CPS040) p.4828 Statistical Inference on Constant Stress Accelerated Life Tests Under Generalized Gamma Lifetime Distributions
More informationGreene, Econometric Analysis (6th ed, 2008)
EC771: Econometrics, Spring 2010 Greene, Econometric Analysis (6th ed, 2008) Chapter 17: Maximum Likelihood Estimation The preferred estimator in a wide variety of econometric settings is that derived
More informationST3241 Categorical Data Analysis I Generalized Linear Models. Introduction and Some Examples
ST3241 Categorical Data Analysis I Generalized Linear Models Introduction and Some Examples 1 Introduction We have discussed methods for analyzing associations in two-way and three-way tables. Now we will
More informationSingle-level Models for Binary Responses
Single-level Models for Binary Responses Distribution of Binary Data y i response for individual i (i = 1,..., n), coded 0 or 1 Denote by r the number in the sample with y = 1 Mean and variance E(y) =
More informationLogistic regression: Miscellaneous topics
Logistic regression: Miscellaneous topics April 11 Introduction We have covered two approaches to inference for GLMs: the Wald approach and the likelihood ratio approach I claimed that the likelihood ratio
More informationDigital Southern. Georgia Southern University. Varadan Sevilimedu Georgia Southern University. Fall 2017
Georgia Southern University Digital Commons@Georgia Southern Electronic Theses & Dissertations Graduate Studies, Jack N. Averitt College of Fall 2017 Application of the Misclassification Simulation Extrapolation
More informationTests of independence for censored bivariate failure time data
Tests of independence for censored bivariate failure time data Abstract Bivariate failure time data is widely used in survival analysis, for example, in twins study. This article presents a class of χ
More informationMultistate models and recurrent event models
and recurrent event models Patrick Breheny December 6 Patrick Breheny University of Iowa Survival Data Analysis (BIOS:7210) 1 / 22 Introduction In this final lecture, we will briefly look at two other
More informationImproving Efficiency of Inferences in Randomized Clinical Trials Using Auxiliary Covariates
Improving Efficiency of Inferences in Randomized Clinical Trials Using Auxiliary Covariates Anastasios (Butch) Tsiatis Department of Statistics North Carolina State University http://www.stat.ncsu.edu/
More informationLeast Squares Estimation
Least Squares Estimation Using the least squares estimator for β we can obtain predicted values and compute residuals: Ŷ = Z ˆβ = Z(Z Z) 1 Z Y ˆɛ = Y Ŷ = Y Z(Z Z) 1 Z Y = [I Z(Z Z) 1 Z ]Y. The usual decomposition
More informationSome General Types of Tests
Some General Types of Tests We may not be able to find a UMP or UMPU test in a given situation. In that case, we may use test of some general class of tests that often have good asymptotic properties.
More informationHypothesis Testing Based on the Maximum of Two Statistics from Weighted and Unweighted Estimating Equations
Hypothesis Testing Based on the Maximum of Two Statistics from Weighted and Unweighted Estimating Equations Takeshi Emura and Hisayuki Tsukuma Abstract For testing the regression parameter in multivariate
More informationModelling geoadditive survival data
Modelling geoadditive survival data Thomas Kneib & Ludwig Fahrmeir Department of Statistics, Ludwig-Maximilians-University Munich 1. Leukemia survival data 2. Structured hazard regression 3. Mixed model
More informationLecture 7 Time-dependent Covariates in Cox Regression
Lecture 7 Time-dependent Covariates in Cox Regression So far, we ve been considering the following Cox PH model: λ(t Z) = λ 0 (t) exp(β Z) = λ 0 (t) exp( β j Z j ) where β j is the parameter for the the
More informationn =10,220 observations. Smaller samples analyzed here to illustrate sample size effect.
Chapter 7 Parametric Likelihood Fitting Concepts: Chapter 7 Parametric Likelihood Fitting Concepts: Objectives Show how to compute a likelihood for a parametric model using discrete data. Show how to compute
More informationMath 423/533: The Main Theoretical Topics
Math 423/533: The Main Theoretical Topics Notation sample size n, data index i number of predictors, p (p = 2 for simple linear regression) y i : response for individual i x i = (x i1,..., x ip ) (1 p)
More informationReduced-rank hazard regression
Chapter 2 Reduced-rank hazard regression Abstract The Cox proportional hazards model is the most common method to analyze survival data. However, the proportional hazards assumption might not hold. The
More informationLecture 12. Multivariate Survival Data Statistics Survival Analysis. Presented March 8, 2016
Statistics 255 - Survival Analysis Presented March 8, 2016 Dan Gillen Department of Statistics University of California, Irvine 12.1 Examples Clustered or correlated survival times Disease onset in family
More informationCIMAT Taller de Modelos de Capture y Recaptura Known Fate Survival Analysis
CIMAT Taller de Modelos de Capture y Recaptura 2010 Known Fate urvival Analysis B D BALANCE MODEL implest population model N = λ t+ 1 N t Deeper understanding of dynamics can be gained by identifying variation
More informationFrailty Modeling for Spatially Correlated Survival Data, with Application to Infant Mortality in Minnesota By: Sudipto Banerjee, Mela. P.
Frailty Modeling for Spatially Correlated Survival Data, with Application to Infant Mortality in Minnesota By: Sudipto Banerjee, Melanie M. Wall, Bradley P. Carlin November 24, 2014 Outlines of the talk
More informationJOINT REGRESSION MODELING OF TWO CUMULATIVE INCIDENCE FUNCTIONS UNDER AN ADDITIVITY CONSTRAINT AND STATISTICAL ANALYSES OF PILL-MONITORING DATA
JOINT REGRESSION MODELING OF TWO CUMULATIVE INCIDENCE FUNCTIONS UNDER AN ADDITIVITY CONSTRAINT AND STATISTICAL ANALYSES OF PILL-MONITORING DATA by Martin P. Houze B. Sc. University of Lyon, 2000 M. A.
More informationBinary choice 3.3 Maximum likelihood estimation
Binary choice 3.3 Maximum likelihood estimation Michel Bierlaire Output of the estimation We explain here the various outputs from the maximum likelihood estimation procedure. Solution of the maximum likelihood
More informationTied survival times; estimation of survival probabilities
Tied survival times; estimation of survival probabilities Patrick Breheny November 5 Patrick Breheny Survival Data Analysis (BIOS 7210) 1/22 Introduction Tied survival times Introduction Breslow approximation
More informationA Very Brief Summary of Statistical Inference, and Examples
A Very Brief Summary of Statistical Inference, and Examples Trinity Term 2008 Prof. Gesine Reinert 1 Data x = x 1, x 2,..., x n, realisations of random variables X 1, X 2,..., X n with distribution (model)
More informationMODULE 6 LOGISTIC REGRESSION. Module Objectives:
MODULE 6 LOGISTIC REGRESSION Module Objectives: 1. 147 6.1. LOGIT TRANSFORMATION MODULE 6. LOGISTIC REGRESSION Logistic regression models are used when a researcher is investigating the relationship between
More informationGeneralized Linear Models
Generalized Linear Models Advanced Methods for Data Analysis (36-402/36-608 Spring 2014 1 Generalized linear models 1.1 Introduction: two regressions So far we ve seen two canonical settings for regression.
More informationREGRESSION ANALYSIS FOR TIME-TO-EVENT DATA THE PROPORTIONAL HAZARDS (COX) MODEL ST520
REGRESSION ANALYSIS FOR TIME-TO-EVENT DATA THE PROPORTIONAL HAZARDS (COX) MODEL ST520 Department of Statistics North Carolina State University Presented by: Butch Tsiatis, Department of Statistics, NCSU
More informationLecture 17: Likelihood ratio and asymptotic tests
Lecture 17: Likelihood ratio and asymptotic tests Likelihood ratio When both H 0 and H 1 are simple (i.e., Θ 0 = {θ 0 } and Θ 1 = {θ 1 }), Theorem 6.1 applies and a UMP test rejects H 0 when f θ1 (X) f
More informationEmpirical Likelihood in Survival Analysis
Empirical Likelihood in Survival Analysis Gang Li 1, Runze Li 2, and Mai Zhou 3 1 Department of Biostatistics, University of California, Los Angeles, CA 90095 vli@ucla.edu 2 Department of Statistics, The
More informationGeneral Linear Model: Statistical Inference
Chapter 6 General Linear Model: Statistical Inference 6.1 Introduction So far we have discussed formulation of linear models (Chapter 1), estimability of parameters in a linear model (Chapter 4), least
More informationKey Words: survival analysis; bathtub hazard; accelerated failure time (AFT) regression; power-law distribution.
POWER-LAW ADJUSTED SURVIVAL MODELS William J. Reed Department of Mathematics & Statistics University of Victoria PO Box 3060 STN CSC Victoria, B.C. Canada V8W 3R4 reed@math.uvic.ca Key Words: survival
More informationCTDL-Positive Stable Frailty Model
CTDL-Positive Stable Frailty Model M. Blagojevic 1, G. MacKenzie 2 1 Department of Mathematics, Keele University, Staffordshire ST5 5BG,UK and 2 Centre of Biostatistics, University of Limerick, Ireland
More informationMultistate models and recurrent event models
Multistate models Multistate models and recurrent event models Patrick Breheny December 10 Patrick Breheny Survival Data Analysis (BIOS 7210) 1/22 Introduction Multistate models In this final lecture,
More information