Statistical methods for survival data analysis / Elisa T. Lee and John Wenyu Wang.

Format:

Book

Author/Creator:

Lee, Elisa T.

Contributor:

Wang, John Wenyu.

Series:

Wiley series in probability and statistics

Language:

English

Subjects (All):

Medicine--Research--Statistical methods.

Medicine.

Failure time data analysis.

Prognosis--Statistical methods.

Prognosis.

Survival Analysis.

Research Design.

Medical Subjects:

Survival Analysis.

Research Design.

Physical Description:

xii, 513 pages : illustrations ; 25 cm.

Edition:

Third edition.

Place of Publication:

New York : J. Wiley, [2003]

Summary:

The Third Edition of the leading reference on survival data analysis

The study of survival data attempts to predict the probability of response, survival, or mean lifetime; compare; the survival distributions of experimental animals or of human patients; and identify risk and/or prognosis factors. Statistical Methods for Survival Data Analysis, Third Edition examines the statistical methods for analyzing survival data from laboratory studies of animals, clinical and epidemiological studies of humans, and other appropriate applications.

Emphasizing applications over rigorous mathematics, this extremely useful reference provides thorough discussions of the most commonly used parametric and nonparametric methods in survival analysis, as well as guidelines for the planning and design of clinical trials. The authors give special consideration to the study of survival data in biomedical sciences, though the methods are suitable for applications in industrial reliability, the social sciences, and business.

This Third Edition brings this standard in the field up to date with new material and revised references including: A new introduction to left and interval censored data The generalized gamma and log-logistic distribution Estimation procedures for left and interval censored data Parametric models with covariates Cox's proportional hazards model including stratification and time-dependent covariates, and some non-proportional hazards models Goodness-of-Fit tests and model selection methods Multiple responses to the logistic regression model Numerous real-life examples which illustrate key concepts Computer programming codes in SAS, BMDP, and SPSS for most examples Related FTPsite providing large data sets

These additions and revisions make Statistical Methods for Survival Data Analysis, Third Edition, more valuable than ever as an essential reference for biomedical investigators, statisticians, epidemiologists, and researchers in other disciplines involved or interested in the analysis of survival data.

Contents:

1.2 Censored Data 1

2 Functions of Survival Time 8

2.2 Relationships of the Survival Functions 15

3 Examples of Survival Data Analysis 19

3.1 Example 3.1: Comparison of Two Treatments and Three Diets 19

3.2 Example 3.2: Comparison of Two Survival Patterns Using Life Tables 26

3.3 Example 3.3: Fitting Survival Distributions to Remission Data 29

3.4 Example 3.4: Relative Mortality and Identification of Prognostic Factors 32

3.5 Example 3.5: Identification of Risk Factors 40

4 Nonparametric Methods of Estimating Survival Functions 64

4.1 Product-Limit Estimates of Survivorship Function 65

4.2 Life-Table Analysis 77

4.3 Relative, Five-Year, and Corrected Survival Rates 94

4.4 Standardized Rates and Ratios 97

5 Nonparametric Methods for Comparing Survival Distributions 106

5.1 Comparison of Two Survival Distributions 106

5.2 Mantel-Haenszel Test 121

5.3 Comparison of K (K [greater than sign] 2) Samples 125

6 Some Well-Known Parametric Survival Distributions and Their Applications 134

6.1 Exponential Distribution 134

6.2 Weibull Distribution 138

6.3 Lognormal Distribution 143

6.4 Gamma and Generalized Gamma Distributions 148

6.5 Log-Logistic Distribution 154

6.6 Other Survival Distributions 155

7 Estimation Procedures for Parametric Survival Distributions without Covariates 162

7.1 General Maximum Likelihood Estimation Procedure 162

7.2 Exponential Distribution 166

7.3 Weibull Distribution 178

7.4 Lognormal Distribution 180

7.5 Standard and Generalized Gamma Distributions 188

7.6 Log-Logistic Distribution 195

7.7 Other Parametric Survival Distributions 196

8 Graphical Methods for Survival Distribution Fitting 198

8.2 Probability Plotting 200

8.3 Hazard Plotting 209

8.4 Cox-Snell Residual Method 215

9 Tests of Goodness of Fit and Distribution Selection 221

9.1 Goodness-of-Fit Test Statistics Based on Asymptotic Likelihood Inferences 222

9.2 Tests for Appropriateness of a Family of Distributions 225

9.3 Selection of a Distribution Using BIC or AIC Procedures 230

9.4 Tests for a Specific Distribution with Known Parameters 233

9.5 Hollander and Proschan's Test for Appropriateness of a Given Distribution with Known Parameters 236

10 Parametric Methods for Comparing Two Survival Distributions 243

10.1 Likelihood Ratio Test for Comparing Two Survival Distributions 243

10.2 Comparison of Two Exponential Distributions 246

10.3 Comparison of Two Weibull Distributions 251

10.4 Comparison of Two Gamma Distributions 252

11 Parametric Methods for Regression Model Fitting and Identification of Prognostic Factors 256

11.1 Preliminary Examination of Data 257

11.2 General Structure of Parametric Regression Models and Their Asymptotic Likelihood Inference 259

11.3 Exponential Regression Model 263

11.4 Weibull Regression Model 269

11.5 Lognormal Regression Model 274

11.6 Extended Generalized Gamma Regression Model 277

11.7 Log-Logistic Regression Model 280

11.8 Other Parametric Regression Models 283

11.9 Model Selection Methods 286

12 Identification of Prognostic Factors Related to Survival Time: Cox Proportional Hazards Model 298

12.1 Partial Likelihood Function for Survival Times 298

12.2 Identification of Significant Covariates 314

12.3 Estimation of the Survivorship Function with Covariates 319

12.4 Adequacy Assessment of the Proportional Hazards Model 326

13 Identification of Prognostic Factors Related to Survival Time: Nonproportional Hazards Models 339

13.1 Models with Time-Dependent Covariates 339

13.2 Stratified Proportional Hazards Models 348

13.3 Competing Risks Model 352

13.4 Recurrent Events Models 356

13.5 Models for Related Observations 374

14 Identification of Risk Factors Related to Dichotomous and Polychotomous Outcomes 377

14.1 Univariate Analysis 378

14.2 Logistic and Conditional Logistic Regression Models for Dichotomous Responses 385

14.3 Models for Polychotomous Outcomes 413

Appendix A Newton-Raphson Method 428.

Notes:

Includes bibliographical references (pages 488-510) and index.

ISBN:

0471369977

OCLC:

50124544