Belinda Barton, Head and Psychologist, Children's Hospital Education Research Institute (CHERI), Conjoint Senior Lecturer, Sydney Medical School, University of Sydney, NSW Australia.

Jennifer Peat, Associate Professor, Department of Paediatrics and Child Health and Senior Hospital Statistician, Clinical Epidemiology Unit, Children's Hospital, Westmead, NSW Australia.

Introduction, ix

Acknowledgements, xiii

About the companion website, xv

Chapter 1 Creating an SPSS data file and preparing to analyse the data, 1

1.1 Creating an SPSS data file, 1

1.2 Opening data from Excel in SPSS, 6

1.3 Categorical and continuous variables, 7

1.4 Classifying variables for analyses, 7

1.5 Hypothesis testing and P values, 8

1.6 Choosing the correct statistical test, 9

1.7 Sample size requirements, 10

1.8 Study handbook and data analysis plan, 12

1.9 Documentation, 13

1.10 Checking the data, 13

1.11 Avoiding and replacing missing values, 14

1.12 SPSS data management capabilities, 16

1.13 Managing SPSS output, 20

1.14 SPSS help commands, 21

1.15 Golden rules for reporting numbers, 21

1.16 Notes for critical appraisal, 21

References, 23

Chapter 2 Descriptive statistics, 24

2.1 Parametric and non-parametric statistics, 25

2.2 Normal distribution, 25

2.3 Skewed distributions, 26

2.4 Checking for normality, 29

2.5 Transforming skewed variables, 43

2.6 Data analysis pathway, 49

2.7 Reporting descriptive statistics, 49

2.8 Checking for normality in published results, 50

2.9 Notes for critical appraisal, 51

References, 51

Chapter 3 Comparing two independent samples, 52

3.1 Comparing the means of two independent samples, 52

3.2 One- and two-sided tests of significance, 54

3.3 Effect sizes, 55

3.4 Study design, 57

3.5 Influence of sample size, 58

3.6 Two-sample t-test, 71

3.7 Confidence intervals, 73

3.8 Reporting the results from two-sample t-tests, 75

3.9 Rank-based non-parametric tests, 80

3.10 Notes for critical appraisal, 88

References, 89

Chapter 4 Paired and one-sample t-tests, 90

4.1 Paired t-tests, 90

4.2 Non-parametric test for paired data, 97

4.3 Standardizing for differences in baseline measurements, 99

4.4 Single-sample t-test, 102

4.5 Testing for a between-group difference, 106

4.6 Notes for critical appraisal, 110

References, 111

Chapter 5 Analysis of variance, 112

5.1 Building ANOVA and ANCOVA models, 113

5.2 ANOVA models, 113

5.3 One-way analysis of variance, 117

5.4 Effect size for ANOVA, 127

5.5 Post-hoc tests for ANOVA, 128

5.6 Testing for a trend, 133

5.7 Reporting the results of a one-way ANOVA, 134

5.8 Factorial ANOVA models, 135

5.9 An example of a three-way ANOVA, 140

5.10 Analysis of covariance (ANCOVA), 145

5.11 Testing the model assumptions of ANOVA/ANCOVA, 149

5.12 Reporting the results of an ANCOVA, 158

5.13 Notes for critical appraisal, 158

References, 160

Chapter 6 Analyses of longitudinal data, 161

6.1 Study design, 161

6.2 Sample size and power, 162

6.3 Covariates, 163

6.4 Assumptions of repeated measures ANOVA and mixed models, 163

6.5 Repeated measures analysis of variance, 164

6.6 Linear mixed models, 182

6.7 Notes for critical appraisal, 195

References, 196

Chapter 7 Correlation and regression, 197

7.1 Correlation coefficients, 197

7.2 Regression models, 205

7.3 Multiple linear regression, 213

7.4 Interactions, 230

7.5 Residuals, 235

7.6 Outliers and remote points, 237

7.7 Validating the model, 240

7.8 Reporting a multiple linear regression, 241

7.9 Non-linear regression, 242

7.10 Centering, 244

7.11 Notes for critical appraisal, 247

References, 247

Chapter 8 Rates and proportions, 249

8.1 Summarizing categorical variables, 249

8.2 Describing baseline characteristics, 251

8.3 Incidence and prevalence, 252

8.4 Chi-square tests, 253

8.5 2 × 3 Chi-square tables, 260

8.6 Cells with small numbers, 262

8.7 Exact chi square test, 263

8.8 Number of cells that can be tested, 264

8.9 Reporting chi-square tests and proportions, 266

8.10 Large contingency tables, 267

8.11 Categorizing continuous variables, 271

8.12 Chi-square trend test for ordered variables, 273

8.13 Number needed to treat (NNT), 277

8.14 Paired categorical variables: McNemar’s chi-square test, 281

8.15 Notes for critical appraisal, 285

References, 286

Chapter 9 Risk statistics, 287

9.1 Risk statistics, 287

9.2 Study design, 288

9.3 Odds ratio, 288

9.4 Protective odds ratios, 296

9.5 Adjusted odds ratios, 298

9.6 Relative risk, 308

9.7 Number needed to be exposed for one additional person to be harmed (NNEH), 312

9.8 Notes for critical appraisal, 312

References, 313

Chapter 10 Tests of reliability and agreement, 314

10.1 Reliability and agreement, 314

10.2 Kappa statistic, 317

10.3 Reliability of continuous measurements, 321

10.4 Intra-class correlation, 322

10.5 Measures of agreement, 325

10.6 Notes for critical appraisal, 329

References, 329

Chapter 11 Diagnostic statistics, 331

11.1 Coding for diagnostic statistics, 331

11.2 Positive and negative predictive values, 332

11.3 Sensitivity and specificity, 335

11.4 Likelihood ratio, 338

11.5 Receiver Operating Characteristic (ROC) Curves, 339

11.6 Notes for critical appraisal, 348

References, 349

Chapter 12 Survival analyses, 350

12.1 Study design, 351

12.2 Censored observations, 351

12.3 Kaplan–Meier survival method, 351

12.4 Cox regression, 360

12.5 Questions for critical appraisal, 368

References, 368

Glossary, 370

Useful websites, 381

Index, 385

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.