Biostatistical Methods (eBook)

John M. Lachin, ScD, is Co-Director of The Biostatistics Center at The George Washington University, where he also serves as Professor of Biostatistics and Epidemiology, and of Statistics. He has published extensively in his areas of research interest, which include sample size evaluation, group sequential methods, analysis of repeated measures, and survival analysis. A Fellow of the American Statistical Association and the Society for Clinical Trials, Dr. Lachin is the coauthor of Randomization in Clinical Trials: Theory and Practice, also published by Wiley.

Preface.

Preface to First Edition.

1 Biostatistics and Biomedical Science.

1.1 Statistics and the Scientific Method.

1.2 Biostatistics.

1.3 Natural History of Disease Progression.

1.4 Types of Biomedical Studies.

1.5 Studies of Diabetic Nephropathy.

2 Relative Risk Estimates and Tests for Independent Groups.

2.1 Probability As a Measure of Risk.

2.2 Measures of Relative Risk.

2.3 Large Sample Distribution.

2.4 Sampling Models Likelihoods.

2.5 Exact Inference.

2.6 Large Sample Inferences.

2.7 SAS PROC FREQ.

2.8 Other Measures of Differential Risk.

2.9 Polychotomous and Ordinal Data.

2.10 Two Independent Groups With Polychotomous Response.

2.11 Multiple Independent Groups.

2.12 Problems.

3 Sample Size, Power, and Efficiency.

3.1 Estimation Precision.

3.2 Power of Z-Tests.

3.3 Test for Two Proportions.

3.4 Power of Chi-Square Tests.

3.5 SAS PROC POWER.

3.6 Efficiency.

3.7 Problems.

4 Stratified-Adjusted Analysis for Independent Groups.

4.1 Introduction.

4.2 Mantel-Haenszel Test and Cochran's Test.

4.3 Stratified-Adjusted Estimators.

4.4 Nature of Covariate Adjustment.

4.5 Multivariate Tests of Hypotheses.

4.6 Tests of Homogeneity.

4.7 Efficient Tests of No Partial Association.

4.8 Asymptotic Relative Efficiency of Competing Tests.

4.9 Maximin-Efficient Robust Tests.

4.10 Random Effects Model.

4.11 Power and Sample Size for Tests of Association.

4.12 Polychotomous and Ordinal Data.

4.13 Problems.

5 Case-Control and Matched Studies.

5.1 Unmatched Case-Control (Retrospective) Sampling.

5.2 Matching.

5.3 Tests of Association for Matched Pairs.

5.4 Measures of Association for Matched Pairs.

5.5 Pair-Matched Retrospective Study.

5.6 Power Function of McNemar's Test.

5.7 Stratified Analysis of Pair-Matched Tables.

5.8 Multiple Matching-Mantel-Haenszel Analysis.

5.9 Matched Polychotomous Data.

5.10 Kappa Index of Agreement.

5.11 Problems.

6 Applications of Maximum Likelihood and Efficient Scores.

6.1 Binomial.

6.2 2x2 Table: Product Binomial (Unconditionally).

6.3 2x2 Table, Conditionally.

6.4 Score-Based Estimate.

6.5 Stratified Score Analysis of Independent 2x2 Tables.

6.6 Matched Pairs.

6.7 Iterative Maximum Likelihood.

6.8 Problems.

7 Logistic Regression Models.

7.1 Unconditional Logistic Regression Model.

7.2 Interpretation of the Logistic Regression Model.

7.3 Tests of Significance.

7.4 Interactions.

7.5 Measures of the Strength of Association.

7.6 Conditional Logistic Regression Model for Matched Sets.

7.7 Models for Polychotomous or Ordinal Data.

7.8 Random Effects and Mixed Models.

7.9 Models for Multivariate or Repeated Measures.

7.10 Problems.

8 Analysis of Count Data.

8.1 Event Rates and the Homogeneous Poisson Model.

8.2 Over Dispersed Poisson Model.

8.3 Poisson Regression Model.

8.4 Over Dispersed and Robust Poisson Regression.

8.5 Conditional Poisson Regression for Matched Sets.

8.6 Negative Binomial Models.

8.7 Power and Sample Size.

8.8 Multiple Outcomes.

8.9 Problems.

9 Analysis of Event-Time Data.

9.1 Introduction to Survival Analysis.

9.2 Lifetable Construction.

9.3 Family of Weighted Mantel-Haenszel Tests.

9.4 Proportional Hazards Models.

9.5 Evaluation of Sample Size and Power.

9.6 Additional Models.

9.7 Analysis of Recurrent Events.

9.8 Problems.

Appendix Statistical Theory.

A.1 Introduction.

A.2 Central Limit Theorem and the Law of Large Numbers.

A.3 Delta Method.

A.4 Slutsky's Convergence Theorem.

A.5 Least Squares Estimation.

A.6 Maximum Likelihood Estimation and Efficient Scores.

A.7 Tests of Significance.

A.8 Explained Variation.

A.9 Robust Inference.

A.10 Generalized Linear Models and Quasi-Likelihood.

A.11 Generalized Estimating Equations (GEE).

References.

Author Index.

Subject Index.

"Biostatistical methods, second edition is an excellent book for
biostatistics courses at the graduate level. It is also an
invaluable reference for biostatisticians, applied statisticians,
and epidemiologists." (Mathematical Reviews, 2011)

"The author of this book has made a tremendous effort in
covering a gamut of tests, methods, and ideas for biostatistical
problem solving . . . In conclusion, the book is recommended to all
in biostatistics as a technical reference." (Journal of
Biopharmaceutical Statistics, 1 September 2012)

"...Biostatistics is set apart from other statistics specialties
by its focus on the assessment of risks and relative risks through
clinical research," states Lachin (George Washington U.) in the
preface to the first edition (2001). He developed this graduate
text to support a course he launched as a joint initiative of the
university's department of statistics, its Biostatistics Center,
and the School of Public Health and Health Services. Coverage
includes discussion of biostatistics and biomedical science,
relative risk estimates and tests for independent groups, sample
size, stratified adjusted analysis, case-control and matched
studies, applications of maximum likelihood and efficient scores,
among other topics." (Book News Inc., February
2011)