Introductory biostatistics for the health sciences : modern applications including bootstrap / Michael R. Chernick, Robert H. Friis.

Format:

Book

Author/Creator:

Chernick, Michael R.

Contributor:

Friis, Robert H.

Alumni and Friends Memorial Book Fund.

Series:

Wiley series in probability and statistics

Language:

English

Subjects (All):

Medical statistics.

Biometry.

Statistics as Topic.

Medical Subjects:

Biometry.

Statistics as Topic.

Physical Description:

xvii, 406 pages : illustrations ; 24 cm.

Place of Publication:

Hoboken, N.J. : Wiley-Interscience, [2003]

Summary:

Statistics is a vital discipline with growing applications across many industries, especially the ever-evolving field of health care, where it plays an essential part in the design of new medical devices, the implementation and analysis of clinical trials, and various epidemiological studies. In today's modern age of computing, both statistical methodology and its applications are expanding as rapidly as the technology will allow, resulting in an upsurge of new developments and more effective methodologies. Introductory Biostatistics for the Health Sciences: Modern Applications Including Bootstrap addresses the need for a book that presents a basic, accurate, and up-to-date overview of statistical methodology as it applies to today's health care industry. The authors, both professionals in the areas of medical consulting and epidemiological research, provide balanced coverage of the latest developments in the industry, liberally illustrated with real-world examples. Students and professionals will find this text helpful in several important ways. A lucid writing style and numerous real-world examples add to the book's appeal and value, and make a complex subject uniquely accessible to a diverse audience including medical personnel, public health trainees, as well as nursing and medical students.

Contents:

1. What is Statistics? How is it Applied in the Health Sciences? 1

1.1 Definitions of Statistics and Statisticians 2

1.2 Why Study Statistics? 3

1.3 Types of Studies 8

1.3.1 Surveys and Cross-Sectional Studies 9

1.3.2 Retrospective Studies 10

1.3.3 Prospective Studies 10

1.3.4 Experimental Studies and Quality Control 10

1.3.5 Clinical Trials 12

1.3.6 Epidemiological Studies 14

1.3.7 Pharmacoeconomic Studies and Quality of Life 16

2. Defining Populations and Selecting Samples 22

2.1 What are Populations and Samples? 22

2.2 Why Select a Sample? 23

2.3 How Samples Can be Selected 25

2.3.1 Simple Random Sampling 25

2.3.2 Convenience Sampling 25

2.3.3 Systematic Sampling 26

2.3.4 Stratified Random Sampling 28

2.3.5 Cluster Sampling 28

2.3.6 Bootstrap Sampling 29

2.4 How to Select a Simple Random Sample 29

2.5 How to Select a Bootstrap Sample 39

2.6 Why Does Random Sampling Work? 41

3. Systematic Organization and Display of Data 46

3.1 Types of Data 46

3.1.1 Qualitative 47

3.1.2 Quantitative 47

3.2 Frequency Tables and Histograms 48

3.3 Graphical Methods 51

3.3.1 Frequency Histograms 51

3.3.2 Frequency Polygons 53

3.3.3 Cumulative Frequency Polygon 54

3.3.4 Stem-and-Leaf Diagrams 56

3.3.5 Box-and-Whisker Plots 58

3.3.6 Bar Charts and Pie Charts 61

4. Summary Statistics 68

4.1 Measures of Central Tendency 61

4.1.1 The Arithmetic Mean 68

4.1.2 The Median 70

4.1.3 The Mode 73

4.1.4 The Geometric Mean 73

4.1.5 The Harmonic Mean 74

4.1.6 Which Measure Should You Use? 75

4.2 Measures of Dispersion 76

4.2.1 Range 78

4.2.2 Mean Absolute Deviation 78

4.2.3 Population Variance and Standard Deviation 79

4.2.4 Sample Variance and Standard Deviation 82

4.2.5 Calculating the Variance and Standard Deviation from Group Data 84

4.3 Coefficient of Variation (CV) and Coefficient of Dispersion (CD) 85

5. Basic Probability 92

5.2 Elementary Sets as Events and Their Complements 95

5.3 Independent and Disjoint Events 95

5.4 Probability Rules 98

5.5 Permutations and Combinations 100

5.6 Probability Distributions 103

5.7 The Binomial Distribution 109

5.8 The Monty Hall Problem 110

5.9 A Quality Assurance Problem 113

6. The Normal Distribution 121

6.1 The Importance of the Normal Distribution in Statistics 121

6.2 Properties of Normal Distributions 122

6.3 Tabulating Areas under the Standard Normal Distribution 124

7. Sampling Distributions for Means 133

7.1 Population Distributions and the Distribution of Sample Averages from the Population 133

7.2 The Central Limit Theorem 141

7.3 Standard Error of the Mean 143

7.4 Z Distribution Obtained When Standard Deviation Is Known 144

7.5 Student's t Distribution Obtained When Standard Deviation Is Unknown 144

7.6 Assumptions Required for t Distribution 147

8. Estimating Population Means 150

8.1 Estimation Versus Hypothesis Testing 150

8.2 Point Estimates 151

8.3 Confidence Intervals 153

8.4 Confidence Intervals for a Single Population Mean 154

8.5 Z and t Statistics for Two Independent Samples 159

8.6 Confidence Intervals for the Difference between Means from Two Independent Samples (Variance Known) 161

8.7 Confidence Intervals for the Difference between Means from Two Independent Samples (Variance Unknown) 161

8.8 Bootstrap Principle 166

8.9 Bootstrap Percentile Method Confidence Intervals 167

8.10 Sample Size Determination for Confidence Intervals 176

9. Tests of Hypotheses 182

9.2 Neyman-Pearson Test Formulation 183

9.3 Test of a Mean (Single Sample, Population Variance Known) 186

9.4 Test of a Mean (Single sample, Population Variance Unknown) 187

9.5 One-Tailed Versus Two-Tailed Tests 188

9.6 p-Values 191

9.7 Type I and Type II Errors 191

9.8 The Power Function 192

9.9 Two-Sample t Test (Independent Samples with a Common Variance) 193

9.10 Paired t Test 195

9.11 Relationship between Confidence Intervals and Hypothesis Tests 199

9.12 Bootstrap Percentile Method Test 200

9.13 Sample Size Determination for Hypothesis Tests 201

9.14 Sensitivity and Specificity in Medical Diagnosis 202

9.15 Meta-Analysis 204

9.16 Bayesian Methods 207

9.17 Group Sequential Methods 209

9.18 Missing Data and Imputation 210

10. Inferences Regarding Proportions 217

10.1 Why Are Proportions Important? 217

10.2 Mean and Standard Deviation for the Binomial Distribution 218

10.3 Normal Approximation to the Binomial 221

10.4 Hypothesis Test for a Single Binomial Proportion 222

10.5 Testing the Difference between Two Proportions 224

10.6 Confidence Intervals for Proportions 225

10.7 Sample Size Determination

Confidence Intervals and Hypothesis Tests 227

11. Categorical Data and Chi-Square Tests 231

11.1 Understanding Chi-Square 232

11.2 Chi-Square Distributions and Tables 233

11.3 Testing Independence between Two Variables 233

11.4 Testing for Homogeneity 236

11.5 Testing for Differences between two Proportions 237

11.6 The Special Case of 2 x 2 Contingency Table 238

11.7 Simpson's Paradox in the 2 x 2 Table 239

11.8 McNemar's Test for Correlated Proportions 241

11.9 Relative Risk and Odds Ratios 242

11.10 Goodness of Fit Tests

Fitting Hypothesized Probability Distributions 244

11.11 Limitations to Chi-Square and Exact Alternatives 246

12. Correlation, Linear Regression, and Logistic Regression 251

12.1 Relationships between Two Variables 252

12.2 Uses of Correlation and Regression 252

12.3 The Scatter Diagram 254

12.4 Pearson's Product Moment Correlation Coefficient and Its Sample Estimate 256

12.5 Testing Hypotheses about the Correlation Coefficient 258

12.6 The Correlation Matrix 259

12.7 Regression Analysis and Least Squares Inference Regarding the Slope and Intercept of a Regression Line 259

12.8 Sensitivity to Outliers, Outlier Rejection, and Robust Regression 264

12.9 Galton and Regression toward the Mean 271

12.10 Multiple Regression 277

12.11 Logistic Regression 283

13. One-Way Analysis of Variance 295

13.1 Purpose of One-Way Analysis of Variance 296

13.2 Decomposing the Variance and Its Meaning 297

13.3 Necessary Assumptions 298

13.4 F Distribution and Applications 298

13.5 Multiple Comparisons 301

13.5.2 Tukey's Honest Significant Difference (HSD) Test 301

14. Nonparametric Methods 308

14.1 Advantages and Disadvantages of Nonparametric Versus Parametric Methods 308

14.2 Procedures for Ranking Data 309

14.3 Wilcoxon Rank-Sum Test 311

14.4 Wilcoxon Signed-Rank Test 314

14.5 Sign Test 317

14.6 Kruskal-Wallis Test: One-Way ANOVA by Ranks 319

14.7 Spearman's Rank-Order Correlation Coefficient 322

14.8 Permutation Tests 324

14.8.1 Introducing Permutation Methods 324

14.8.2 Fisher's Exact Test 327

14.9 Insensitivity of Rank Tests to Outliers 330

15. Analysis of Survival Times 336

15.1 Introduction to Survival Times 336

15.2 Survival Probabilities 338

15.2.2 Life Tables 339

15.2.3 The Kaplan-Meier Curve 341

15.2.4 Parametric Survival Curves 344

15.2.5 Cure Rate Models 348

15.3 Comparing Two or More Survival Curves

The Log Rank Test 349

16. Software Packages for Statistical Analysis 356

A Percentage Points, F-Distribution ([alpha] = 0.05) 363

B Studentized Range Statistics 364

C Quantiles of the Wilcoxon Signed-Rank Test Statistic 366

D x[superscript 2] Distribution 368

E Table of the Standard Normal Distribution 370

F Percentage Points, Student's t Distribution 371.

Notes:

Includes bibliographical references and index.

Local Notes:

Acquired for the Penn Libraries with assistance from the Alumni and Friends Memorial Book Fund.

ISBN:

047141137X

OCLC:

50866922