JIM FOWLER, former Principal Lecturer, Department of Biological Sciences, De Montfort University, Leicester, UK.PHILIP JARVIS, Statistician, Novartis Pharma AG, Basel, Switzerland.MEL CHEVANNES, Emeritus Professor of Nursing, University of Wolverhampton, Wolverhampton, UK.

"The language is friendly and puts the reader at ease ....This book provides comprehensive coverage of an area that is important to all health care professionals. (Nursing Times, 28 March 2002)"...a plain English guide...to facilitate both learning and reference..." (Nurse Education Today, No.23,2003)"...helpful in enabling nurses to appraise empirical research and utilise research in their practice..." (Primary Health Care, October 2003)"...provides clear explanations of the statistical concepts and illustrates these using relevant nursing scenarios..." (Practice Nurse, Friday 16 January, 2004)"...provides a basic foundation of statistics...good resource for nurses...very user friendly..." (Oncology Nursing Forum, Vol31(2), 2004)

• Preface xiForeword to Students xv1 Introduction 11.1 What Do we Mean by Statistics? 11.2 Why Is Statistics Necessary? 11.3 The Limitations of Statistics 21.4 Performing Statistical Calculations 21.5 The Purpose of this Text 22 Health Care Investigations: Measurement and Sampling Concepts 52.1 Introduction 52.2 Populations, Samples and Observations 52.3 Counting Things – The Sampling Unit 62.4 Sampling Strategy 62.5 Target and Study Populations 72.6 Sample Designs 72.7 Simple Random Sampling 82.8 Systematic Sampling 92.9 Stratified Sampling 92.10 Quota Sampling 102.11 Cluster Sampling 112.12 Sampling Designs – Summary 112.13 Statistics and Parameters 112.14 Descriptive and Inferential Statistics 122.15 Parametric and Non-Parametric Statistics 123 Processing Data 133.1 Scales of Measurement 133.2 The Nominal Scale 133.3 The Ordinal Scale 143.4 The Interval Scale 143.5 The Ratio Scale 153.6 Conversion of Interval Observations to an Ordinal Scale 153.7 Derived Variables 163.8 Logarithms 173.9 The Precision of Observations 183.10 How Precise Should We Be? 193.11 The Frequency Table 193.12 Aggregating Frequency Classes 213.13 Frequency Distribution of Count Observations 233.14 Bivariate Data 234 Presenting Data 254.1 Introduction 254.2 Dot Plot or Line Plot 254.3 Bar Graph 264.4 Histogram 284.5 Frequency Polygon and Frequency Curve 294.6 Centiles and Growth Charts 294.7 Scattergram 324.8 Circle or Pie Graph 325 Clinical Trials 355.1 Introduction 355.2 The Nature of Clinical Trials 355.3 Clinical Trial Designs 365.4 Psychological Effects and Blind Trials 375.5 Historical Controls 385.6 Ethical Issues 385.7 Case Study: Leicestershire Electroconvulsive Therapy Study 385.8 Summary 406 Introduction to Epidemiology 416.1 Introduction 416.2 Measuring Disease 426.3 Study Designs – Cohort Studies 436.4 Study Designs – Case-Control Studies 456.5 Cohort or Case-Control Study? 466.6 Choice of Comparison Group 466.7 Confounding 476.8 Summary 487 Measuring the Average 497.1 What Is an Average? 497.2 The Mean 497.3 Calculating the Mean of Grouped Data 517.4 The Median – A Resistant Statistic 527.5 The Median of a Frequency Distribution 537.6 The Mode 547.7 Relationship between Mean, Median and Mode 558 Measuring Variability 578.1 Variability 578.2 The Range 578.3 The Standard Deviation 588.4 Calculating the Standard Deviation 598.5 Calculating the Standard Deviation from Grouped Data 608.6 Variance 618.7 An Alternative Formula for Calculating the Variance and Standard Deviation 618.8 Degrees of Freedom 628.9 The Coefficient of Variation 639 Probability and the Normal Curve 659.1 The Meaning of Probability 659.2 Compound Probabilities 669.3 Critical Probability 679.4 Probability Distribution 689.5 The Normal Curve 699.6 Some Properties of the Normal Curve 709.7 Standardizing the Normal Curve 719.8 Two-Tailed or One-Tailed? 729.9 Small Samples: The t-Distribution 749.10 Are our Data Normally Distributed? 759.11 Dealing with ‘Non-normal’ Data 7710 How Good Are our Estimates? 8110.1 Sampling Error 8110.2 The Distribution of a Sample Mean 8110.3 The Confidence Interval of a Mean of a Large Sample 8310.4 The Confidence Interval of a Mean of a Small Sample 8510.5 The Difference between the Means of Two Large Samples 8610.6 The Difference between the Means of Two Small Samples 8810.7 Estimating a Proportion 8910.8 The Finite Population Correction 9011 The Basis of Statistical Testing 9111.1 Introduction 9111.2 The Experimental Hypothesis 9111.3 The Statistical Hypothesis 9211.4 Test Statistics 9311.5 One-Tailed and Two-Tailed Tests 9311.6 Hypothesis Testing and the Normal Curve 9411.7 Type 1 and Type 2 Errors 9511.8 Parametric and Non-parametric Statistics: Some Further Observations 9611.9 The Power of a Test 9712 Analysing Frequencies 9912.1 The Chi-Square Test 9912.2 Calculating the Test Statistic 9912.3 A Practical Example of a Test for Homogeneous Frequencies 10212.4 One Degree of Freedom – Yates’ Correction 10312.5 Goodness of Fit Tests 10412.6 The Contingency Table – Tests for Association 10512.7 The ‘Rows by Columns’ (r × c) Contingency Table 10812.8 Larger Contingency Tables 10912.9 Advice on Analysing Frequencies 11113 Measuring Correlations 11313.1 The Meaning of Correlation 11313.2 Investigating Correlation 11313.3 The Strength and Significance of a Correlation 11513.4 The Product Moment Correlation Coefficient 11613.5 The Coefficient of Determination r2 11813.6 The Spearman Rank Correlation Coefficient rs 11813.7 Advice on Measuring Correlations 12014 Regression Analysis 12114.1 Introduction 12114.2 Gradients and Triangles 12114.3 Dependent and Independent Variables 12214.4 A Perfect Rectilinear Relationship 12314.5 The Line of Least Squares 12514.6 Simple Linear Regression 12614.7 Fitting the Regression Line to the Scattergram 12814.8 Regression for Estimation 12814.9 The Coefficient of Determination in Regression 12914.10 Dealing with Curved Relationships 12914.11 How Can We ‘Straighten Up’ Curved Relationships? 13214.12 Advice on Using Regression Analysis 13315 Comparing Averages 13515.1 Introduction 13515.2 Matched and Unmatched Observations 13615.3 The Mann–Whitney U-Test for Unmatched Samples 13615.4 Advice on Using the Mann–Whitney U-Test 13715.5 More than Two Samples – The Kruskal–Wallis Test 13815.6 Advice on Using the Kruskal–Wallis Test 14015.7 The Wilcoxon Test for Matched Pairs 14015.8 Advice on Using the Wilcoxon Test for Matched Pairs 14315.9 Comparing Means – Parametric Tests 14315.10 The z-Test for Comparing the Means of Two Large Samples 14415.11 The t-Test for Comparing the Means of Two Small Samples 14515.12 The t-Test for Matched Pairs 14615.13 Advice on Comparing Means 14716 Analysis of Variance – ANOVA 14916.1 Why Do We Need ANOVA? 14916.2 How ANOVA Works 14916.3 Procedure for Computing ANOVA 15116.4 The Tukey Test 15416.5 Further Applications of ANOVA 15516.6 Advice on Using ANOVA 157AppendicesAppendix A: Table of Random Numbers 159Appendix B: t-Distribution 160Appendix C: χ2-Distribution 162Appendix D: Critical Values of Spearman’s Rank Correlation Coefficient 164Appendix E: Critical Values of the Product Moment Correlation Coefficient 166Appendix F: Mann–Whitney U-test Values (Two-Tailed Test) P =0.05 169Appendix G: Critical Values of T in the Wilcoxon Test for Matched Pairs 170Appendix H: F-Distribution 173Appendix I: Tukey Test 178Appendix J: Symbols 180Appendix K: Leicestershire ECT Study Data: Subgroup with Depressive Illness 183Appendix L: How Large Should Our Samples Be? 187Bibliography 193Index 195