Statistical Advances in the Biomedical Sciences: Clinical Trials, Epidemiology, Survival Analysis, and Bioinformatics (Wiley Series in Probability and Statistics)

Statistical Advances in the Biomedical Sciences......Page 4
Contents......Page 10
Preface......Page 24
Acknowledgments......Page 28
Contributors......Page 30
PART I CLINICAL TRIALS......Page 34
1.2 Phase I Trials in Healthy Volunteers......Page 36
1.3 Phase I Trials with Toxic Outcomes Enrolling Patients......Page 38
1.3.2 Markovian-Motivated Up-and-Down Designs......Page 39
1.3.4 Bayesian Designs......Page 42
1.3.5 Time-to-Event Design Modifications......Page 43
1.4 Other Design Problems in Dose Finding......Page 44
1.5 Concluding Remarks......Page 45
2.1.1 Background......Page 48
2.1.2 The Role of Phase II Clinical Trials in Clinical Evaluation of a Novel Therapeutic Agent......Page 49
2.1.3 Phase II Clinical Trial Designs......Page 50
2.2.1 Review of Frequentist Methods and Their Applications in Phase II Clinical Trials......Page 51
2.2.2 Frequentist Methods for Single-Treatment Pilot Studies......Page 52
2.2.3 Frequentist Methods for Comparative Studies......Page 54
2.3.1 Review of Bayesian Methods and Their Application in Phase II Clinical Trials......Page 55
2.3.2 Bayesian Methods for Single-Treatment Pilot Studies, Comparative Studies and Selection Screens......Page 57
2.4 Decision-Theoretic Methods in Phase II Clinical Trials......Page 58
2.5 Analysis of Multiple Endpoints in Phase II Clinical Trials......Page 59
2.6 Outstanding Issues in Phase II Clinical Trials......Page 60
3.1 Introduction......Page 66
3.2.2 Randomized Play-the-Winner Design......Page 67
3.2.3 Generalized Pólya’s Urn (GPU)......Page 68
3.2.4 Randomized Pólya Urn Design......Page 69
3.2.7 Drop-the-Loser Urn Design......Page 70
3.2.8 Sequential Estimation-Adjusted Urn Design......Page 71
3.2.9 Doubly Adaptive Biased Coin Design......Page 72
3.3.1 Covariate-Adaptive Randomized Play-the-Winner Design......Page 73
3.4 Adaptive Designs for Categorical Responses......Page 74
3.5.1 Nonparametric-Score-Based Allocation Designs......Page 75
3.6 Optimal Adaptive Designs......Page 76
3.7 Delayed Responses in Adaptive Designs......Page 77
3.9 Real Adaptive Clinical Trials......Page 78
3.10.1 Fluoxetine Trial......Page 79
3.10.2 Pregabalin Trial......Page 80
3.10.3 Simulated Trial......Page 81
3.11 Concluding Remarks......Page 82
4.1 Introduction......Page 88
4.1.1 Inverse Binomial Sampling......Page 89
4.1.2 Partial Sequential Sampling......Page 91
4.2.1 Use of Mann–Whitney Statistics......Page 92
4.2.2 Fixed-Width Confidence Interval Estimation......Page 93
4.2.3 Fixed-Width Confidence Interval for Partial Sequential Sampling......Page 94
4.4 Inverse Sampling in Adaptive Designs......Page 95
4.5 Concluding Remarks......Page 96
5.1 Introduction: Cluster Randomized Trials......Page 100
5.2 Intracluster Correlation Coefficient and Confidence Interval......Page 102
5.3 Sample Size Calculation for Cluster Randomized Trials......Page 104
5.4 Analysis of Cluster Randomized Trial Data......Page 106
5.5 Concluding Remarks......Page 108
PART II EPIDEMIOLOGY......Page 114
6.1 Introduction......Page 116
6.2.1 HIV Dynamic Model......Page 117
6.2.2 Treatment Effect Models......Page 118
6.3.1 Bayesian Nonlinear Mixed-Effects Model......Page 120
6.3.2 Predictions Using the Bayesian Mixed-Effects Modeling Approach......Page 122
6.4 Simulation Study......Page 123
6.5 Clinical Data Analysis......Page 124
6.6 Concluding remarks......Page 125
7.1 Space and Disease......Page 130
7.2 Basic Spatial Questions and Related Data......Page 131
7.3 Quantifying Pattern in Point Data......Page 132
7.4 Predicting Spatial Observations......Page 140
7.5 Concluding Remarks......Page 151
8.1 Introduction......Page 156
8.2 Data Analysis via Population Models......Page 157
8.3 Sequential Monte Carlo......Page 159
8.4 Modeling Cholera......Page 163
8.4.1 Fitting Structural Models to Cholera Data......Page 165
8.5 Concluding Remarks......Page 169
9.1 Introduction......Page 174
9.2.3 Effect of Maternal Dietary Habits on Low Birth Weight in Babies......Page 176
9.3 Binary Regression Models with Two Types of Error......Page 177
9.4 Bivariate Binary Regression Models with Two Types of Error......Page 179
9.5 Models for Analyzing Mixed Misclassified Binary and Continuous Responses......Page 182
9.6 Atom Bomb Data Analysis......Page 184
9.7 Concluding Remarks......Page 185
PART III SURVIVAL ANALYSIS......Page 190
10.1 Introduction......Page 192
10.2 Examples of Survival Models......Page 193
10.3 Basic Estimation and Limit Theory......Page 195
10.4 The Bootstrap......Page 196
10.4.1 The Regular Case......Page 198
10.5 The Profile Sampler......Page 199
10.6 The Piggyback Bootstrap......Page 201
10.7 Other Approaches......Page 203
10.8 Concluding Remarks......Page 204
11.1 Introduction......Page 210
11.2 Nonparametric Inferences......Page 212
11.3 Semiparametric One-Sample Inference......Page 214
11.4 Semiparametric Regression Method......Page 217
11.4.1 Functional Regression Modeling......Page 218
11.4.2 A Bivariate Accelerated Lifetime Model......Page 220
11.5 Concluding Remarks......Page 222
12.1 Introduction......Page 226
12.2 Model Specification and Inferential Procedures......Page 227
12.2.1 A Pseudo–Score Test......Page 230
12.3.1 Simulation Studies......Page 232
12.3.2 Trace Data......Page 235
12.5 Summary......Page 237
Appendix 12A......Page 238
13.1 Introduction......Page 242
13.2 Induced Dependent Censoring and Associated Identifiability Issues......Page 243
13.3.1 Hazard Functions with Marked Point Process......Page 245
13.3.3 Nonparametric Estimation......Page 246
13.3.4 Martingales......Page 247
13.4 Modeling Strategy for Testing and Regression......Page 248
13.4.2 Calibration Regression for Lifetime Medical Cost......Page 249
13.4.3 Two-Sample Multistate Accelerated Sojourn-Time Model......Page 250
13.5 Concluding Remarks......Page 251
14.1 Introduction......Page 254
14.2.2 Inverse Censoring Probability Weighted Estimators......Page 256
14.2.3 NPMLE-Type Estimators......Page 257
14.2.4 Data Application to Danish Twin Data......Page 259
14.3.1 Nonparametric Dependence Estimation......Page 263
14.3.2 Semiparametric Dependence Estimation......Page 265
14.3.3 An Application to a Case–Control Family Study of Breast Cancer......Page 269
14.4 Concluding Remarks......Page 272
15.1 Introduction......Page 278
15.2.1 Estimation in the Presence of Only Independent Censoring (with All Censoring Variables Observable)......Page 280
15.2.2 Estimation in the Presence of Terminal Events......Page 281
15.3 Large-Sample Properties......Page 282
15.4.1 Simulation Studies......Page 285
15.4.2 rhDNase Data......Page 290
15.5 Concluding Remarks......Page 292
Appendix 15A......Page 293
16.1 Introduction......Page 298
16.2 Review of CART......Page 299
16.3.1 Methods Based on Measure of Within-Node Homogeneity......Page 301
16.3.2 Methods Based on Between-Node Separation......Page 304
16.4 Simulations for Comparison of Different Splitting Methods......Page 305
16.5 Example: Breast Cancer Prognostic Study......Page 307
16.6 Random Forest for Survival Data......Page 311
16.6.1 Breast Cancer Study: Results from Random Forest Analysis......Page 313
16.7 Concluding Remarks......Page 314
17.1 Introduction......Page 320
17.1.1 The Random Right-Censorship Model......Page 322
17.1.2 The Bayesian Model......Page 323
17.2 Bayesian Functional Model Using Monotone Wavelet Approximation......Page 325
17.3 Estimation of the Subdensity F*......Page 328
17.4 Simulations......Page 329
17.5 Examples......Page 331
17.6 Concluding Remarks......Page 333
Appendix 17A......Page 334
PART IV BIOINFORMATICS......Page 340
18.1 Introduction......Page 342
18.2 Intergene Correlation......Page 343
18.3 Differential Expression......Page 347
18.4 Timecourse Experiments......Page 348
18.5 Meta-Analysis......Page 352
18.6 Concluding Remarks......Page 354
19.1 Introduction......Page 358
19.2.1 Technology Details and Gene Identification......Page 359
19.2.2 Analysis Methods......Page 360
19.3 Example......Page 361
19.5 Best Common Mean Difference Method......Page 362
19.6 Effect Size Method......Page 364
19.7 POE Assimilation Method......Page 365
19.8 Comparison of Three Methods......Page 367
19.8.2 Classification Performance......Page 368
19.9 Conclusions......Page 369
20.1 Introduction......Page 374
20.2 Normalization......Page 377
20.3 Methods for Selecting Differentially Expressed Genes......Page 382
20.3.1 BH-T......Page 383
20.3.2 SAM......Page 384
20.3.3 SPH......Page 385
20.3.4 LIMMA......Page 387
20.3.5 MAANOVA......Page 388
20.4 Simulation Study......Page 390
20.4.1 Results of Simulation Studies......Page 392
20.5 Concluding Remarks......Page 393
21.1 Introduction......Page 398
21.3 Notation......Page 400
21.4 Clustering of Tissue Samples......Page 402
21.5.1 Step 1.Screening of Genes......Page 403
21.5.2 Step 2.Clustering of Genes: Formation of Metagenes......Page 404
21.6 Clustering of Gene Profiles......Page 405
21.7 EMMIX-WIRE......Page 406
21.8 Maximum-Likelihood Estimation via the EM Algorithm......Page 407
21.9 Model Selection......Page 409
21.10 Example: Clustering of Timecourse Data......Page 410
21.11 Concluding Remarks......Page 412
22.1 Introduction......Page 418
22.2.1 The Cox Proportional Hazards Model......Page 419
22.2.2 Accelerated Failure-Time Model......Page 420
22.3 Regularized Estimation for Censored Data Regression Models......Page 421
22.3.1 L(2) Penalized Estimation of the Cox Model Using Kernels......Page 422
22.3.2 L(1) Penalized Estimation of the Cox Model Using Least-Angle Regression......Page 423
22.3.4 Regularized Buckley–James Estimation for the AFT Model......Page 424
22.3.5 Regularization Based on Inverse Probability of Censoring Weighted Loss Function for the AFT Model......Page 425
22.3.6 Penalized Estimation for the Additive Hazard Model......Page 426
22.4.1 The Smoothing-Spline-Based Boosting Algorithm for the Nonparametric Additive Cox Model......Page 427
22.5 Nonparametric-Pathway-Based Regression Models......Page 428
22.6 Dimension-Reduction-Based Methods and Bayesian Variable Selection Methods......Page 429
22.8 Application to a Real Dataset and Comparisons......Page 430
22.9 Discussion and Future Research Topics......Page 431
22.9.2 Development of Flexible Models for Gene–Gene and Gene–Environment Interactions......Page 432
22.10 Concluding Remarks......Page 433
23.1 Introduction......Page 438
23.2 Maximum-Likelihood Analysis of Case–Control Data with Complete Information......Page 439
23.2.1 Background......Page 440
23.2.2 Maximum-Likelihood Estimation under HWE and Gene–Environment Independence......Page 441
23.3.1 Background......Page 443
23.3.2 Methods......Page 445
23.3.3 Application......Page 447
23.4 Concluding Remarks......Page 448
24.1 Introduction......Page 452
24.2 Graphs of Biological Data......Page 453
24.3 Statistics on Graphs......Page 454
24.4 Graph-Theoretic Models......Page 455
24.5.1 Stochastic Error......Page 458
24.6 Exploratory Data Analysis......Page 459
24.6.2 Sampling......Page 460
24.6.3 Underlying Network Structure......Page 461
24.7.1 Path Length: L......Page 462
24.7.2 Clustering Coefficient: C......Page 464
24.8.1 Experimental Data......Page 469
24.9 Conclusions......Page 472
25.1 Introduction......Page 476
25.1.1 Biologic Overview of Splicing......Page 477
25.2.1 Maximum-Entropy Models......Page 478
25.2.2 Permuted Variable-Length Markov Models......Page 480
25.2.3 Bayesian Network Approaches......Page 481
25.3 Splice Site Recognition via Contemporary Classifiers......Page 483
25.3.1 Random Forests......Page 484
25.3.3 Boosting......Page 487
25.4.2 Predictive Performance......Page 488
25.4.3 Interpretational Yield......Page 490
25.4.4 Computational Considerations......Page 491
25.5 Concluding Remarks......Page 492
26.1. Introduction......Page 498
26.1.1 Sample Ionization......Page 500
26.1.2 Mass Analysis......Page 501
26.3 Statistical Methods for Preprocessing......Page 503
26.4.1 Multiple Testing and Identification of Differentially Expressed Peaks......Page 506
26.4.3 A Semiparametric Model for Protein Mass Spectroscopy......Page 507
26.4.4 Smoothed Principal-Component Analysis (PCA) for Proteomic Spectra......Page 509
26.4.5 Wavelet-Based Functional Mixed Model and Application......Page 510
26.4.6 A Nonparametric Bayesian Model Based on Kernel Functions......Page 512
26.5 Potential Statistical Developments......Page 514
26.6 Concluding Remarks......Page 516
27.1 Introduction......Page 520
27.2 The Basic QTL Framework For Sib-Pairs......Page 521
27.4 Nonparametric Alternatives......Page 522
27.5 The Modified Nonparametric Regression......Page 523
27.5.1 Evaluation of Significance Levels......Page 524
27.6 Comparison With Linear Regression Methods......Page 525
27.7 Significance Levels and Empirical Power......Page 526
27.8 An Application to Real Data......Page 528
27.9 Concluding Remarks......Page 529
PART V MISCELLANEOUS TOPICS......Page 532
28.1 Introduction: The Need for Robust Procedures......Page 534
28.2 Standard Tools for Robustness......Page 535
28.2.2 Influence Function......Page 536
28.2.4 Basic Miscellaneous Procedures......Page 537
28.2.5 Alternative Approaches......Page 538
28.3 The Robustness Question in Biomedical Studies......Page 539
28.4 Robust Estimation in the Logistic Regression Model......Page 541
28.5 Robust Estimation for Censored Survival Data......Page 546
28.6 Adaptive Robust Methods in Clinical Trials......Page 551
28.7 Concluding Remarks......Page 554
29.1 Introduction......Page 560
29.2 A General Biophysical Model......Page 563
29.3 Bayesian deconvolution model (BDM)......Page 564
29.3.1 Posterior Processing......Page 567
29.3.2 An Example......Page 569
29.4 Nonlinear Mixed-Effects Partial-Splines Models......Page 570
29.5 Concluding Remarks......Page 575
30.1 Introduction......Page 580
30.2 Statistical Models......Page 582
30.3 Multistage Models......Page 585
30.4 Two-Stage Clonal Expansion Model......Page 588
30.5 Physiologically Based Pharmacokinetic Models......Page 593
30.6 Statistical Methods......Page 595
30.7 Concluding Remarks......Page 597
Index......Page 602