Basic Biostatistics for Geneticists and Epidemiologists: A Practical Approach

Anyone who attempts to read genetics or epidemiology research literature needs to understand the essentials of biostatistics. This book, a revised new edition of the successful Essentials of Biostatistics has been written to provide such an understanding to those who have little or no statistical background and who need to keep abreast of new findings in this fast moving field. Unlike many other elementary books on biostatistics, the main focus of this book is to explain basic concepts needed to understand statistical procedures. This Book: Surveys basic statistical methods used in the genetics and epidemiology literature, including maximum likelihood and least squares. Introduces methods, such as permutation testing and bootstrapping, that are becoming more widely used in both genetic and epidemiological research. Is illustrated throughout with simple examples to clarify the statistical methodology. Explains Bayes’ theorem pictorially. Features exercises, with answers to alternate questions, enabling use as a course text. Written at an elementary mathematical level so that readers with high school mathematics will find the content accessible. Graduate students studying genetic epidemiology, researchers and practitioners from genetics, epidemiology, biology, medical research and statistics will find this an invaluable introduction to statistics.

Table of Contents:
Preface ix 1 Introduction: The Role and Relevance of Statistics, Genetics and Epidemiology In Medicine 3 Why Biostatistics? 3 What Exactly is (Are) Statistics? 5 Reasons for Understanding Statistics 6 What Exactly is Genetics? 8 What Exactly is Epidemiology? 10 How Can a Statistician Help Geneticists and Epidemiologists? 11 Disease Prevention versus Disease Therapy 12 A Few Examples: Genetics, Epidemiology and Statistical Inference 12 Summary 14 References 15 2 Populations, Samples, and Study Design 19 The Study of Cause and Effect 19 Populations, Target Populations and Study Units 21 Probability Samples and Randomization 23 Observational Studies 25 Family Studies 27 Experimental Studies 28 Quasi-Experimental Studies 36 Summary 37 Further Reading 38 Problems 38 3 Descriptive Statistics 45 Why Do We Need Descriptive Statistics? 45 Scales of Measurement 46 Tables 47 Graphs 49 Proportions and Rates 55 Relative Measures of Disease Frequency 58 Sensitivity, Specificity and Predictive Values 61 Measures of Central Tendency 62 Measures of Spread or Variability 64 Measures of Shape 67 Summary 68 Further Reading 70 Problems 70 4 The Laws of Probability 79 Definition of Probability 79 The Probability of Either of Two Events: A or B 82 The Joint Probability of Two Events: A and B 83 Examples of Independence, Nonindependence and Genetic Counseling 86 Bayes’ Theorem 89 Likelihood Ratio 97 Summary 98 Further Reading 99 Problems 99 5 Random Variables and Distributions 107 Variability and Random Variables 107 Binomial Distribution 109 A Note about Symbols 112 Poisson Distribution 113 Uniform Distribution 114 Normal Distribution 116 Cumulative Distribution Functions 119 The Standard Normal (Gaussian) Distribution 120 Summary 122 Further Reading 123 Problems 123 6 Estimates and Confidence Limits 131 Estimates and Estimators 131 Notation for Population Parameters, Sample Estimates, and Sample Estimators 133 Properties of Estimators 134 Maximum Likelihood 135 Estimating Intervals 137 Distribution of the Sample Mean 138 Confidence Limits 140 Summary 146 Problems 148 7 Significance Tests and Tests of Hypotheses 155 Principle of Significance Testing 155 Principle of Hypothesis Testing 156 Testing a Population Mean 157 One-Sided versus Two-Sided Tests 160 Testing a Proportion 161 Testing the Equality of Two Variances 165 Testing the Equality of Two Means 167 Testing the Equality of Two Medians 169 Validity and Power 172 Summary 176 Further Reading 178 Problems 178 8 Likelihood Ratios, Bayesian Methods and Multiple Hypotheses 187 Likelihood Ratios 187 Bayesian Methods 190 Bayes’ Factors 192 Bayesian Estimates and Credible Intervals 194 The Multiple Testing Problem 195 Summary 198 Problems 199 9 The Many Uses of Chi-Square 203 The Chi-Square Distribution 203 Goodness-of-Fit Tests 206 Contingency Tables 209 Inference About the Variance 219 Combining p-Values 220 Likelihood Ratio Tests 221 Summary 223 Further Reading 225 Problems 225 10 Correlation and Regression 233 Simple Linear Regression 233 The Straight-Line Relationship When There is Inherent Variability 240 Correlation 242 Spearman’s Rank Correlation 246 Multiple Regression 246 Multiple Correlation and Partial Correlation 250 Regression toward the Mean 251 Summary 253 Further Reading 254 Problems 255 11 Analysis of Variance and Linear Models 265 Multiple Treatment Groups 265 Completely Randomized Design with a Single Classification of Treatment Groups 267 Data with Multiple Classifications 269 Analysis of Covariance 281 Assumptions Associated with the Analysis of Variance 282 Summary 283 Further Reading 284 Problems 285 12 Some Specialized Techniques 293 Multivariate Analysis 293 Discriminant Analysis 295 Logistic Regression 296 Analysis of Survival Times 299 Estimating Survival Curves 301 Permutation Tests 304 Resampling Methods 309 Summary 312 Further Reading 313 Problems 313 13 Guides To a Critical Evaluation of Published Reports 321 The Research Hypothesis 321 Variables Studied 321 The Study Design 322 Sample Size 322 Completeness of the Data 323 Appropriate Descriptive Statistics 323 Appropriate Statistical Methods for Inferences 323 Logic of the Conclusions 324 Meta-analysis 324 Summary 326 Further Reading 327 Problems 328 Epilogue 329 Review Problems 331 Answers to Odd-Numbered Problems 345 Appendix 353 Index 365