Edward E Gbur, Walter W Stroup, Kevin S McCarter, Susan Durham, Linda J Young, Mary Christman, Mark West, Matthew Kramer

Generalized Linear Mixed Model

• Gebundenes Buch

Produktbeschreibung

Generalized Linear Mixed Models in the Agricultural and Natural Resources Sciences provides readers with an understanding and appreciation for the design and analysis of mixed models for non-normally distributed data. It is the only publication of its kind directed specifically toward the agricultural and natural resources sciences audience. Readers will especially benefit from the numerous worked examples based on actual experimental data and the discussion of pitfalls associated with incorrect analyses.

---

Hinweis: Dieser Artikel kann nur an eine deutsche Lieferadresse ausgeliefert werden.

Produktdetails

• Verlag: Wiley
• Seitenzahl: 304
• Erscheinungstermin: 22. Januar 2020
• Englisch
• Abmessung: 235mm x 157mm x 21mm
• Gewicht: 590g
• ISBN-13: 9780891181828
• ISBN-10: 0891181822
• Artikelnr.: 58460247

Autorenporträt

Edward Gbur is currently Professor and Interim Director of the Agricultural Statistics Laboratory at the University of Arkansas. Previously he was on the faculty in the Statistics Department at Texas A&M University and was a Mathematical Statistician in the Statistical Research Division at the Census Bureau. He received a Ph.D. in Statistics from The Ohio State University. He is a member and Fellow of the American Statistical Association and a member of the International Biometric Society and the Institute of Mathematical Statistics. His current research interests include experimental design, generalized linear mixed models, stochastic modeling, and agricultural applications of statistics. Walter Stroup is Professor of Statistics at the University of Nebraska, Lincoln. After receiving his Ph.D. in Statistics from the University of Kentucky in 1979, he joined the Biometry faculty at Nebraska's Institute of Agriculture and Natural Resources. He served as teacher, researcher and consultant until becoming department chair in 2001. In 2003, Biometry was incorporated into a new Department of Statistics at UNL; Walt served as chair from its founding through 2010. He is co-author of SAS for Mixed Models and SAS for Linear Models. He is a member of the International Biometric Society, American Association for the Advancement of Science and a member and Fellow of the American Statistical Association. His interests include design of experiments and statistical modeling. Kevin S. McCarter is a faculty member in the Department of Experimental Statistics at Louisiana State University. He earned the Bachelors degree with majors in Mathematics and Computer Information Systems from Washburn University, and the Masters and Ph.D. degrees in Statistics from Kansas State University. He has industry experience as an IT professional in banking, accounting, and health care, and as a biostatistician in the pharmaceutical industry. His dissertation research was in the area of survival analysis. His current research interests include predictive modeling, developing and assessing statistical methodology, and applying generalized linear mixed modeling techniques. He has collaborated with researchers from a wide variety of fields including agriculture, biology, education, medicine, and psychology. Susan Durham is a statistical consultant at Utah State University, collaborating with faculty and graduate students in the Ecology Center, Biology Department, and College of Natural Resources. She earned a Bachelors degree in Zoology at Oklahoma State University and a Masters degree in Applied Statistics at Utah State University. Her interests cover the broad range of research problems that have been brought to her as a statistical consultant. Mary Christman is currently the lead statistical consultant with MCC Statistical Consulting LLC, which provides statistical expertise for environmental and ecological problems. She is also courtesy professor at the University of Florida (UF). She was on the faculty at UF, University of Maryland, and American University after receiving her PhD in statistics from George Washington University. She is a member of several organizations including the American Statistical Association (ASA), the International Environmetrics Society, and the American Association for the Advancement of Science. She received the 2004 Distinguished Achievement Award from the Section on Statistics and the Environment of the ASA. Her current research interests include linear and non-linear modeling in the presence of correlated error terms, sampling and experimental design, and statistical methodology for ecological and environmental research. Linda J. Young is Professor of Statistics at the University of Florida. She completed her Ph.D. in Statistics at Oklahoma State University and has previously served on the faculties of Oklahoma State University and the University of Nebraska-Lincoln. Linda has served the profession in a variety of capacities, including President of the Eastern North American Region of the International Biometric Society, Treasurer of the International Biometric Society, Vice-President of the American Statistical Association, and Chair of the Committee of Presidents of Statistical Societies. She has co-authored two books and has more than 100 refereed publications. She is a fellow of the American Association for the Advancement of Science, a fellow of the American Statistical Association, and an elected member of the International Statistical Institute. Her research interests include spatial statistics and statistical modeling. Mark West is a statistician for the U. S. Department of Agriculture Agricultural Research Service. He received his Ph.D. in Applied Statistics from the University of Alabama in 1989 and has been a statistical consultant in agriculture research ever since beginning his professional career at Auburn University in 1989. His interests include experimental design, statistical computing, computer intensive methods, and generalized linear mixed models. Matt Kramer is a statistician in the mid-Atlantic area (Beltsville, MD) of the Agricultural Research Service (USDA), where he has worked since 1999. Prior to that, he spent eight years at the Census Bureau in the Statistical Research Division (time series and small area estimation). He received a Masters and Ph.D. from the University of Tennessee. His interests are in basic biological and ecological statistical applications.

Inhaltsangabe

Foreword vii
Preface ix
Authors xi
Conversion Factors for SI and Non-SI Units xiii
Chapter 1 Introduction 1
1.1 Introduction 1
1.2 Generalized Linear Mixed Models 2
1.3 Historical Development 3
1.4 Objectives of this Book 5
Chapter 2 Background 7
2.1 Introduction 7
2.2 Distributions used in Generalized Linear Modeling 7
2.3 Descriptions of the Distributions 10
2.4 Likelihood Based Approach to Estimation 15
2.5 Variations on Maximum Likelihood Estimation 18
2.6 Likelihood Based Approach to Hypo
2.7 Computational Issues 22
2.8 Fixed, Random, and Mixed Models 24
2.9 The Design-Analysis of Variance-Generalized Linear Mixed Model
Connection 25
2.10 Conditional versus Marginal Models 30
2.11 Software 30
Chapter 3 Generalized Linear Models 35
3.1 Introduction 35
3.2 Inference in Generalized Linear Models 37
3.3 Diagnostics and Model Fit 46
3.4 Generalized Linear Modeling versus Transformations 52
Chapter 4 Linear Mixed Models 59
4.1 Introduction 59
4.2 Estimation and Inference in Linear Mixed Models 60
4.3 Conditional and Marginal Models 61
4.4 Split Plot Experiments 67
4.5 Experiments Involving Repeated Measures 77
4.6 Selection of a Covariance Model 78
4.7 A Repeated Measures Example 80
4.8 Analysis of Covariance 88
4.9 Best Linear Unbiased Prediction 99
Chapter 5 Generalized Linear Mixed Models 109
5.1 Introduction 109
5.2 Estimation and Inference in Generalized Linear Mixed Models 110
5.3 Conditional and Marginal Models 111
5.4 Three Simple Examples 125
5.5 Over-Dispersion in Generalized Linear Mixed Models 149
5.6 Over-Dispersion from an Incorrectly Specified Distribution 151
5.7 Over-Dispersion from an Incorrect Linear Predictor 160
5.8 Experiments Involving Repeated Measures 167
5.9 Inference Issues for Repeated Measures Generalized Linear Mixed Models
181
5.10 Multinomial Data 184
Chapter 6 More Complex Examples 199
6.1 Introduction 199
6.2 Repeated Measures in Time and Space 199
6.3 Analysis of a Precision Agriculture Experiment 210
Chapter 7 Designing Experiments 237
7.1 Introduction 237
7.2 Power and Precision 238
7.3 Power and Precision Analyses for Generalized Linear Mixed Models 239
7.4 Methods of Determining Power and Precision 241
7.5 Implementation of the Probability Distribution Method 243
7.6 A Factorial Experiment with Different Design Options 250
7.7 A Multi-location Experiment with a Binomial Response Variable 255
7.8 A Split Plot Revisited with a Count as the Response Variable 262
7.9 Summary and Conclusions 268
Chapter 8 Parting Thoughts and Future Directions 271
8.1 The Old Standard Statistical Practice 271
8.2 The New Standard 272
8.3 The Challenge to Adapt 274
Index 277