Bayesian Population Analysis using WinBUGS

Bayesian statistics has exploded into biology and its sub-disciplines, such as ecology, over the past decade. The free software program WinBUGS, and its open-source sister OpenBugs, is currently the only flexible and general-purpose program available with which the average ecologist can conduct standard and non-standard Bayesian statistics.

• Comprehensive and richly commented examples illustrate a wide range of models that are most relevant to the research of a modern population ecologist
• All WinBUGS/OpenBUGS analyses are completely integrated in software R
• Includes complete documentation of all R and WinBUGS code required to conduct analyses and shows all the necessary steps from having the data in a text file out of Excel to interpreting and processing the output from WinBUGS in R

Professional ecologists, upper-level graduate and graduate ecology students

Dedication

Foreword

Preface

Acknowledgments

Chapter 1. Introduction

1.1. Ecology: The Study of Distribution and Abundance and of the Mechanisms Driving Their Change

1.2. Genesis of Ecological Observations

1.3. The Binomial Distribution as a Canonical Description of the Observation Process

1.4. Structure and Overview of the Contents of this Book

1.5. Benefits of Analyzing Simulated Data Sets: An Example of Bias and Precision

1.6. Summary and Outlook

1.7. Exercises

Chapter 2. Brief Introduction to Bayesian Statistical Modeling

2.1. Introduction

2.2. Role of Models in Science

2.3. Statistical Models

2.4. Frequentist and Bayesian Analysis of Statistical Models

2.5. Bayesian Computation

2.6. WinBUGS

2.7. Advantages and Disadvantages of Bayesian Analyses by Posterior Sampling

2.8. Hierarchical Models

2.9. Summary and Outlook

Chapter 3. Introduction to the Generalized Linear Model

3.1. Introduction

3.2. Statistical Models: Response = Signal + Noise

3.3. Poisson GLM in R and WinBUGS for Modeling Time Series of Counts

3.4. Poisson GLM for Modeling Fecundity

3.5. Binomial GLM for Modeling Bounded Counts or Proportions

3.6. Summary and Outlook

3.7. Exercises

Chapter 4. Introduction to Random Effects

4.1. Introduction

4.2. Accounting for Overdispersion by Random Effects-Modeling in R and WinBUGS

4.3. Mixed Models with Random Effects for Variability among Groups (Site and Year Effects)

4.4. Summary and Outlook

4.5. Exercises

Chapter 5. State-Space Models for Population Counts

5.1. Introduction

5.2. A Simple Model

5.3. Systematic Bias in the Observation Process

5.4. Real Example: House Martin Population Counts in the Village of Magden

5.5. Summary and Outlook

5.6. Exercises

Chapter 6. Estimation of the Size of a Closed Population from Capture–Recapture Data

6.1. Introduction

6.2. Generation and Analysis of Simulated Data with Data Augmentation

6.3. Analysis of a Real Data Set: Model Mtbh for Species Richness Estimation

6.4. Capture–Recapture Models with Individual Covariates: Model Mt+X

6.5. Summary and Outlook

6.6. Exercises

Chapter 7. Estimation of Survival from Capture–Recapture Data Using the Cormack–Jolly–Seber Model

7.1. Introduction

7.2. The CJS Model as a State-Space Model

7.3. Models with Constant Parameters

7.4. Models with Time-Variation

7.5. Models with Individual Variation

7.6. Models with Time and Group Effects

7.7. Models with Age Effects

7.8. Immediate Trap Response in Recapture Probability

7.9. Parameter Identifiability

7.10. Fitting the CJS to Data in the M-Array Format: the Multinomial Likelihood

7.11. Analysis of a Real Data Set: Survival of Female Leisler's Bats

7.12. Summary and Outlook

7.13. Exercises

Chapter 8. Estimation of Survival Using Mark-Recovery Data

8.1. Introduction

8.2. The Mark-Recovery Model as a State-Space Model

8.3. The Mark-Recovery Model Fitted with the Multinomial Likelihood

8.4. Real-Data Example: Age-Dependent Survival in Swiss Red Kites

8.5. Summary and Outlook

8.6. Exercises

Chapter 9. Estimation of Survival and Movement from Capture–Recapture Data Using Multistate Models

9.1. Introduction

9.2. Estimation of Movement between Two Sites

9.3. Accounting for Temporary Emigration

9.4. Estimation of Age-Specific Probability of First Breeding

9.5. Joint Analysis of Capture–Recapture and Mark-Recovery Data

9.6. Estimation of Movement among Three Sites

9.7. Real-Data Example: The Showy Lady's Slipper

9.8. Summary and Outlook

9.9. Exercises

Chapter 10. Estimation of Survival, Recruitment, and Population Size from Capture–Recapture Data Using the Jolly–Seber Model

10.1. Introduction

10.2. The JS Model as a State-Space Model

10.3. Fitting the JS Model with Data Augmentation

10.4. Models with Constant Survival and Time-Dependent Entry

10.5. Models with Individual Capture Heterogeneity

10.6. Connections between Parameters, Further Quantities and Some Remarks on Identifiability

10.7. Analysis of a Real Data Set: Survival, Recruitment and Population Size of Leisler's Bats

10.8. Summary and Outlook

10.9. Exercises

Chapter 11. Estimation of Demographic Rates, Population Size, and Projection Matrices from Multiple Data Types Using Integrated Population Models

11.1. Introduction

11.2. Developing an Integrated Population Model (IPM)

11.3. Example of a Simple IPM (Counts, Capture–Recapture, Reproduction)

11.4. Another Example of an IPM: Estimating Productivity without Explicit Productivity Data

11.5. IPMs for Population Viability Analysis

11.6. Real Data Example: Hoopoe Population Dynamics

11.7. Summary and Outlook

11.8. Exercises

Chapter 12. Estimation of Abundance from Counts in Metapopulation Designs Using the Binomial Mixture Model

12.1. Introduction

12.2. Generation and Analysis of Simulated Data

12.3. Analysis of Real Data: Open-Population Binomial Mixture Models

12.4. Summary and Outlook

12.5. Exercises

Chapter 13. Estimation of Occupancy and Species Distributions from Detection/Nondetection Data in Metapopulation Designs Using Site-Occupancy Models

13.1. Introduction

13.2. What Happens When p < 1 and Constant and p is Not Accounted for in a Species Distribution Model?

13.3. Generation and Analysis of Simulated Data for Single-Season Occupancy

13.4. Analysis of Real Data Set: Single-Season Occupancy Model

13.5. Dynamic (Multiseason) Site-Occupancy Models

13.6. Multistate Occupancy Models

13.7. Summary and Outlook

13.8. Exercises

Chapter 14. Concluding Remarks

14.1. The Power and Beauty of Hierarchical Models

14.2. The Importance of the Observation Process

14.3. Where Will We Go?

14.4. The Importance of Population Analysis for Conservation and Management

Appendix 1. A List of WinBUGS Tricks

Appendix 2. Two Further Useful Multistate Capture–Recapture Models

References

Index