Contents -- Preface -- Part I Analysis of Survival and Longitudinal Data -- Chapter 1 Non- and Semi- Parametric Modeling in Survival Analysis Jianqing Fan, Jiancheng Jiang. -- 1 Introduction. -- 2 Cox's type of models -- 2.1 Cox's models with unknown nonlinear risk functions -- 2.2 Partly linear Cox's models -- 2.3 Partly linear additive Cox's models -- 3 Multivariate Cox's type of models. -- 3.1 Marginal modeling using Cox's models with linear risks -- 3.2 Marginal modeling using Cox's models with nonlinear risks -- 3.3 Marginal modeling using partly linear Cox's models -- 3.4 Marginal modeling using partly linear Cox's models with varying coefficients -- 4 Model selection on Cox's models -- 5 Validating Cox's type of models. -- 6 Transformation models. -- 7 Concluding remarks -- References. -- Chapter 2 Additive-Accelerated Rate Model for Recurrent Event Donglin Zeng, Jianwen Cai -- 1 Introduction. -- 2 Inference procedure and asymptotic properties. -- 3 Assessing additive and accelerated covariates -- 4 Simulation studies. -- 5 Application -- 6 Remarks -- Acknowledgements -- Appendix -- References. -- Chapter 3 An Overview on Quadratic Inference Function Approaches for Longitudinal Data John J. Dziak, Runze Li, Annie Qu -- 1 Introduction -- 2 The quadratic inference function approach. -- 2.1 Generalized estimating equations -- 2.2 Quadratic inference functions -- 3 Penalized quadratic inference function. -- 3.1 Time-varying coefficient models -- 3.2 Variable selection for longitudinal data -- 4 Some applications of QIF -- 4.1 Missing data -- 4.2 Outliers and contamination -- 4.3 A real data example -- 5 Further research and concluding remarks. -- Acknowledgements. -- References. -- Chapter 4 Modeling and Analysis of Spatially Correlated Data Yi Li -- 1 Introduction -- 2 Basic concepts of spatial process.

2.1 Spatial regression models for normal data -- 2.2 Spatial prediction (Kriging) -- 3 Spatial models for non-normal/discrete data -- 3.1 Spatial generalized linear mixed models (SGLMMs) -- 3.2 Computing MLEs for SGLMMs -- 4 Spatial models for censored outcome data -- 4.1 A class of semiparametric estimation equations -- 4.2 Asymptotic Properties and Variance Estimation -- 4.3 A data example: east boston asthma study -- 5 Concluding remarks. -- References. -- Part II Statistical Methods for Epidemiology -- Chapter 5 Study Designs for Biomarker-Based Treatment Selection Amy Laird, Xiao-Hua Zhou. -- 1 Introduction -- 2 Definition of study designs. -- 2.1 Traditional design -- 2.2 Marker by treatment interaction design -- 2.3 Marker-based strategy design -- 2.4 Modified marker-based strategy design -- 2.5 Targeted design -- 3 Test of hypotheses and sample size calculation. -- 3.1 Test for equality -- 3.2 Test for non-inferiority or superiority -- 3.3 Test for equivalence -- 4 Sample size calculation -- 4.1 Traditional design -- 4.2 Marker by treatment interaction design -- 4.3 Marker-based strategy design -- 4.4 Modified marker-based strategy design -- 4.5 Targeted design -- 5 Numerical comparisons of efficiency. -- 5.1 Marker by treatment interaction design -- 5.2 Marker-based strategy design -- 5.3 Modified marker-based strategy design -- 5.4 Targeted design -- 6 Conclusions -- Acknowledgements -- Appendix. -- A.I Traditional design -- A.2 Marker by treatment interaction design -- A.3 Marker-based strategy design -- A.4 Modified marker-based strategy design -- References -- Chapter 6 Statistical Methods for Analyzing Two-Phase Studies Jinbo Chen -- 1 Introduction -- 2 Two-phase case-control or cross-sectional studies. -- 2.1 Estimating-equation approaches for analyzing two-pha se case-control studies.

2.2 Nonparametric maximum likelihood analysis of two-ph a se case-control studies -- 2.3 Weighted method, pseudo-likelihood method, and NPM LE method -- 3 Two-phase designs in cohort studies -- 3.1 Case-Cohort and stratified case-cohort design -- 3.1.1 Weighted likelihood/estimating equation approaches -- 3.1.2 Pseudo-likelihood estimators -- 3.1.3 Nonparametric maximum likelihood estimation -- 3.1.4 Selection of a method for analysis -- 3.2 Nested case-control and counter-matching design -- 3.2.1 Methods for analyzing the nested case-control data -- 3.2.2 Methods for analyzing counter-matched data -- 3.2.3 Unmatched case-control studies -- 3.2.4 Comparing study designs and analysis approaches -- 4 Conclusions -- References -- Part III Bioinformatics -- Chapter 7 Protein Interaction Predictions from Diverse Sources Yin Liu, Inyoung Kim, Hongyu Zhao -- 1 Introduction -- 2 Data sources useful for protein interaction predictions -- 3 Domain-based methods -- 3.1 Maximum likelihood-based methods (MLE) -- 3.2 Bayesian methods (BAY) -- 3.3 Domain pair exclusion analysis (DPEA) -- 3.4 Parsimony explanation method (PE) -- 4 Classification methods -- 4.1 Integrating different types of genomic information -- 4.2 Gold standard datasets -- 4.3 Prediction performance comparison -- 5 Complex detection methods -- 5.1 Graph theoretic based methods -- 5.2 Graph clustering methods -- 5.3 Performance comparison -- 6 Conclusions -- Acknowledgements -- References -- Chapter 8 Regulatory Motif Discovery: From Decoding to Meta-Analysis Qing Zhou, Mayetri Gupta -- 1 Introduction -- 2 A Bayesian approach to motif discovery. -- 2.1 Markov chain Monte Carlo computation -- 2.2 Some extensions of the product-multinomial model -- 3 Discovery of regulatory modules. -- 3.1 A hybrid EMC-DA approach: EMCmodule -- 3.1.1 Evolutionary Monte Carlo for module selection.

3.1.2 Sampling motif sites A through recursive DA -- 3.2 A case-study -- 4 Motif discovery in multiple species. -- 4.1 The coupled hidden Markov model -- 4.2 Gibbs sampling and Bayesian inference -- 4.3 Simulation studies -- 5 Motif learning on ChIP-chip data -- 5.1 Feature extraction -- 5.2 Bayesian additive regression trees -- 5.3 Application to human ChIP-chip data -- 6 Using nucleosome positioning information in motif discovery.. -- 6.1 A hierarchical generalized HMM (HGHMM) -- 6.2 Model fitting and parameter estimation -- 6.3 Application to a yeast data set -- 7 Conclusion -- References. -- Chapter 9 Analysis of Cancer Genome Alterations Using Single Nucleotide Polymorphism (SNP) Microarrays Cheng Li, Samir Amin -- 1 Background. -- 1.1 Cancer genomic alterations -- 1.2 Identifying cancer genomic alterations using oligonucleotide SNP microarrays -- 2 Loss of heterozygosity analysis using SNP arrays. -- 2.1 LOH analysis of paired normal and tumor samples -- 2.2 Tumor-only LOH inference -- 3 Copy number analysis using SNP arrays -- 3.1 Obtaining raw copy numbers from SNP array data -- 3.2 Inferring integer copy numbers -- 3.3 Copy number analysis results of the 10K dataset -- 3.4 Allele-specific copy numbers and major copy proportion -- 3.5 Copy number variations in normal samples and other diseases -- 3.6 Other copy number analysis methods for SNP array data -- 4 High-level analysis using LOH and copy number data -- 4.1 Finding significantly altered chromosome regions across multiple samples -- 4.2 Hierarchical clustering analysis -- 4.3 Integrating SNP array data with gene expression data -- 5 Software for cancer alteration analysis using SNP arrays. -- 5.1 The dChip software for analyzing SNP array data -- 5.2 Other software packages -- 6 Prospects -- Acknowledgements. -- References.

Chapter 10 Analysis of ChIP-chip Data on Genome Tiling Microarrays W. Evan Johnson, Jun S. Liu, X. Shirley Liu -- 1 Background molecular biology. -- 2 A ChIP-chip experiment -- 2.1 Chromatin immunoprecipitation -- 2.2 Hybridization to a tiling microarray -- 2.3 Early ChIP-chip experiments -- 2.4 Commercial tiling microarrays -- 3 Data description and analysis. -- 3.1 Low-level analysis -- 3.2 High-level analysis -- 4 Follow-up analysis. -- 4.1 Correlating ChIP-chip and Gene Expression Data -- 4.2 Scanning sequences for known motifs -- 4.3 Identifying new binding motifs -- 4.3.1 Regular expression enumeration -- 4.3.2 Position weight matrix update -- 4.4 Using microarrays to guide motif search -- 5 Conclusion -- References -- Subject Index. -- Author Index.