Complex Data Modeling and Computationally Intensive Statistical Methods

yjlxn

Complex Data Modeling and Computationally Intensive Statistical Methods
ISBN: 8847013852
标签: 科学工程
Pietro Mantovan, Piercesare Secchi, “Complex Data Modeling and Computationally Intensive Statistical Methods”
Springer | 2010 | ISBN: 8847013852 | 176 pages | PDF | 2 MB


The last years have seen the advent and development of many devices able to record and store an always increasing amount of complex and high dimensional data; 3D images generated by medical scanners or satellite remote sensing, DNA microarrays, real time financial data, system control datasets. The analysis of this data poses new challenging problems and requires the development of novel statistical models and computational methods, fueling many fascinating and fast growing research areas of modern statistics. The book offers a wide variety of statistical methods and is addressed to statisticians working at the forefront of statistical analysis.



Table of Contents

List of Contributors

Space-time texture analysis in thermal infrared imaging for classification of Raynaud’s Phenomenon

1 Introduction

2 TheData

3 Processing thermal high resolution infrared images

3.1 Segmentation

3.2 Registration

4 Feature extraction

4.1 ST-GMRFs

4.2 Texture statistics through co-occurrence matrices

5 Classification results

6 Conclusions

References

Mixed-effects modelling of Kevlar fibre failure times through Bayesian non-parametrics

1 Introduction

2 Accelerated life models for Kevlar fibre life data

3 The Bayesian semiparametric AFT model

4 Data analysis

5 Conclusions

Appendix

References

Space filling and locally optimal designs for Gaussian Universal Kriging

1 Introduction

2 Kriging methodology

3 Optimality of space filling designs

4 Locally optimal designs for Universal Kriging

4.1 Optimal designs for estimation

4.2 Optimal designs for prediction

5 Conclusions

References

Exploitation, integration and statistical analysis of the Public Health Database and STEMI Archive in the Lombardia region

1 Introduction

2 The MOMI2 study

3 The STEMI Archive

4 The Public Health Database

4.1 Healthcare databases

4.2 Health information systems in Lombardia

5 The statistical perspective

5.1 Frailty models

5.2 Generalised linear mixed models

5.3 Bayesian hierarchical models

6 Conclusions

References

Bootstrap algorithms for variance estimation in PS sampling

1 Introduction

2 The na飗e boostrap

3 Holmberg’s PS bootstrap

4 The 0.5 PS-bootstrap

5 The x-balanced PS-bootstrap

6 Simulation study

7 Conclusions

References

Fast Bayesian functional data analysis of basal body temperature

1 Introduction

2 Methods

2.1 RVM in linear models

2.2 Extension to linear mixed model

3 Results: application to bbt data

3.1 Subject-specific profiles

3.2 Subject-specific and population average profiles

3.3 Prediction

4 Conclusions

References

A parametric Markov chain to model age- andstate-dependent wear processes

1 Introduction

2 System description and preliminary technological considerations

3 Data description and preliminary statistical considerations

4 Model description

5 Parameter estimation

6 Testing dependence on time and/or state

7 Conclusions

References

Case studies in Bayesian computation using INLA

1 Introduction

2 Latent Gaussian models

3 Integrated Nested Laplace Approximation

4 The INLA package for R

5 Case studies

5.1 A GLMM with over-dispersion

5.2 Childhood undernutrition in Zambia: spatial analysis

5.3 A simple example of survival data analysis

6 Conclusions

References

A graphical models approach for comparing gene sets

1 Introduction

2 A brief introduction to pathways

3 Data and graphical models setup

4 Test of equality of two concentration matrices

5 Conclusions

References

Predictive densities and prediction limits based onpredictive likelihoods

1 Introduction

2 Review on predictive methods

2.1 Plug-in predictive procedures and improvements

2.2 Profile predictive likelihood and modifications

3 Likelihood-based predictive distributions and prediction limits

3.1 Probability distributions from predictive likelihoods

3.2 Prediction limits and coverage probabilities

4 Examples

4.1 Prediction limits for the sum of future Gaussian observations

4.2 Prediction limits for the maximum of future Gaussian observations

Appendix

References

Computer-intensive conditional inference

1 Introduction

2 An inference problem

3 Exponential family and ancillary statistic models

4 Analytic approximations

5 Bootstrap approximations

6 Examples

6.1 Inverse Gaussian distribution

6.2 Log-normal mean

6.3 Weibull distribution

6.4 Exponential regression

7 Conclusions

References

Monte Carlo simulation methods for reliability estimation and failure prognostics

1 Introduction

2 The subset and line sampling methods for realiability estimat】
ion

3 Particle filtering for failure prognosis

4 Conclusions

References


http://www.filesonic.com/file/72691265