A Practical Approach to Using Statistics in Health Research: From Planning to Reporting

DescriptionA Practical Approach to Using Statistics in Health Research offers an easy to use, step-by-step guide for using statistics in health research. The authors use their experience of statistics and health research to explain how statistics fit in to all stages of the research process. They explain how to determine necessary sample sizes, interpret whether there are statistically significant difference in outcomes between groups, and use measured effect sizes to decide whether any changes are large enough to be relevant to professional practice.The text walks you through how to identify the main outcome measure for your study and the factor which you think may influence that outcome and then determine what type of data will be used to record both of these. It then describes how this information is used to select the most appropriate methods to report and analyze your data. A step-by-step guide on how to use a range of common statistical procedures are then presented in separate chapters. To help you make sure that you are using statistics robustly, the authors also explore topics such as multiple testing and how to check whether measured data follows a normal distribution. Videos showing how to use computer packages to carry out all the various methods mentioned in the book are available on our companion web site. This book:Covers statistical aspects of all the stages of health research from planning to final reportingExplains how to report statistical planning, how analyses were performed, and the results and conclusionPuts the spotlight on consideration of clinical significance and not just statistical significanceExplains the importance of reporting 95% confidence intervals for effect sizeIncludes a systematic guide for selection of statistical tests and uses example data sets and videos to help you understand exactly how to use statisticsWritten as an introductory guide to statistics for healthcare professionals, students and lecturers in the fields of pharmacy, nursing, medicine, dentistry, physiotherapy, and occupational therapy, A Practical Approach to Using Statistics in Health Research:From Planning to Reporting is a handy reference that focuses on the application of statistical methods within the health research context.Table of ContentsIntroduction 1At Whom is This Book Aimed? 1At What Scale of Project is This Book Aimed? 2Why Might This Book be Useful for You? 2How to Use This Book 3Computer Based Statistics Packages 4Relevant Videos etc. 5Data Types 7What Types of Data are There and Why Does it Matter? 7Continuous Measured Data 7Continuous Measured Data – Normal and Non‐Normal Distribution 8Transforming Non‐Normal Data 13Ordinal Data 13Categorical Data 14Ambiguous Cases 14A Continuously Varying Measure that has been Divided into a Small Number of Ranges 14Composite Scores with a Wide Range of Possible Values 15Relevant Videos etc. 15Presenting and Summarizing Data 17Continuous Measured Data 17Normally Distributed Data – Using the Mean and Standard Deviation 18Data With Outliers, e.g. Skewed Data – Using Quartiles and the Median 18Polymodal Data – Using the Modes 20Ordinal Data 21Ordinal Scales With a Narrow Range of Possible Values 22Ordinal Scales With a Wide Range of Possible Values 22Dividing an Ordinal Scale Into a Small Number of Ranges (e.g. Satisfactory/Unsatisfactory or Poor/Acceptable/Good) 22Summary for Ordinal Data 23Categorical Data 23 Relevant Videos etc. 24Appendix 1: An Example of the Insensitivity of the Median When Used to Describe Data from an Ordinal Scale With a Narrow Range of Possible Values 25Choosing a Statistical Test 27Identify the Factor and Outcome 27Identify the Type of Data Used to Record the Relevant Factor 29Statistical Methods Where the Factor is Categorical 30Identify the Type of Data Used to Record the Outcome 30Is Continuous Measured Outcome Data Normally Distributed or Can It Be Transformed to Normality? 30Identify Whether Your Sets of Outcome Data Are Related or Independent 31For the Factor, How Many Levels Are Being Studied? 32Determine the Appropriate Statistical Method for Studies with a Categorical Factor 32Correlation and Regression with a Measured Factor 34What Type of Data Was Used to Record Your Factor and Outcome? 34When Both the Factor and the Outcome Consist of Continuous Measured Values, Select Between Pearson and Spearman Correlation 34Relevant Additional Material 38Multiple Testing 39What Is Multiple Testing and Why Does It Matter? 39What Can We Do to Avoid an Excessive Risk of False Positives? 40Use of Omnibus Tests 40Distinguishing Between Primary and Secondary/ Exploratory Analyses 40Bonferroni Correction 41Common Issues and Pitfalls 43Determining Equality of Standard Deviations 43How Do I Know, in Advance, How Large My SD Will Be? 43One‐Sided Versus Two‐Sided Testing 44Pitfalls That Make Data Look More Meaningful Than It Really Is 45Too Many Decimal Places 45Percentages with Small Sample Sizes 47Discussion of Statistically Significant Results 47Discussion of Non‐Significant Results 50Describing Effect Sizes with Non‐Parametric Tests 51Confusing Association with a Cause and Effect Relationship 52Contingency Chi‐Square Test 55When Is the Test Appropriate? 55An Example 55Presenting the Data 57Contingency Tables 57Clustered or Stacked Bar Charts 57Data Requirements 59An Outline of the Test 59Planning Sample Sizes 59Carrying Out the Test 60Special Issues 61Yates Correction 61Low Expected Frequencies – Fisher’s Exact Test 61Describing the Effect Size 61Absolute Risk Difference (ARD) 62Number Needed to Treat (NNT) 63Risk Ratio (RR) 63Odds Ratio (OR) 64Case: Control Studies 65How to Report the Analysis 65Methods 65Results 66Discussion 67Confounding and Logistic Regression 67Reporting the Detection of Confounding 68Larger Tables 69Collapsing Tables 69Reducing Tables 70Relevant Videos etc. 71Independent Samples (Two‐Sample) T‐Test 73When Is the Test Applied? 73An Example 73Presenting the Data 75Numerically 75Graphically 75Data Requirements 75Variables Required 75Normal Distribution of the Outcome Variable Within the Two Samples 75Equal Standard Deviations 78Equal Sample Sizes 78An Outline of the Test 78Planning Sample Sizes 79Carrying Out the Test 79Describing the Effect Size 79How to Describe the Test, the Statistical and Practical Significance of Your Findings in Your Report 80Methods Section 80Results Section 80Discussion Section 81Relevant Videos etc. 81Mann–Whitney Test 83When Is the Test Applied? 83An Example 83Presenting the Data 85Numerically 85Graphically 85Divide the Outcomes into Low and High Ranges 85Data Requirements 86Variables Required 86Normal Distributions and Equality of Standard Deviations 87Equal Sample Sizes 87An Outline of the Test 87Statistical Significance 87Planning Sample Sizes 87Carrying Out the Test 88Describing the Effect Size 88How to Report the Test 89Methods Section 89Results Section 89Discussion Section 90Relevant Videos etc. 91One‐Way Analysis of Variance (ANOVA) – Including Dunnett’s and Tukey’s Follow Up Tests 93When Is the Test Applied? 93An Example 93Presenting the Data 94Numerically 94Graphically 94Data Requirements 94Variables Required 94Normality of Distribution for the Outcome Variable Within the Three Samples 95Standard Deviations 96Sample Sizes 98An Outline of the Test 98Follow Up Tests 98Planning Sample Sizes 99Carrying Out the Test 100Describing the Effect Size 101How to Report the Test 101Methods 101Results Section 102Discussion Section 102Relevant Videos etc. 103Kruskal–Wallis 105When Is the Test Applied? 105An Example 105Presenting the Data 106Numerically 106Graphically 107Data Requirements 109Variables Required 109Normal Distributions and Standard Deviations 109Equal Sample Sizes 110An Outline of the Test 110Planning Sample Sizes 110Carrying Out the Test 110Describing the Effect Size 111Determining Which Group Differs from Which Other 111How to Report the Test 111Methods Section 111Results Section 112Discussion Section 113Relevant Videos etc. 114McNemar’s Test 115When Is the Test Applied? 115An Example 115Presenting the Data 116Data Requirements 116An Outline of the Test 118Planning Sample Sizes 118Carrying Out the Test 119Describing the Effect Size 119How to Report the Test 119Methods Section 119Results Section 120Discussion Section 120Relevant Videos etc. 121Paired T‐Test 123When Is the Test Applied? 123An Example 125Presenting the Data 125Numerically 125Graphically 125Data Requirements 126Variables Required 126Normal Distribution of the Outcome Data 126Equal Standard Deviations 128Equal Sample Sizes 128An Outline of the Test 128Planning Sample Sizes 129Carrying Out the Test 129Describing the Effect Size 129How to Report the Test 130Methods Section 130Results Section 130Discussion Section 131Relevant Videos etc. 131Wilcoxon Signed Rank Test 133When Is the Test Applied? 133An Example 134Presenting the Data 134Numerically 134Graphically 136Data Requirements 136Variables Required 136Normal Distributions and Equal Standard Deviations 137Equal Sample Sizes 137An Outline of the Test 137Planning Sample Sizes 138Carrying Out the Test 139Describing the Effect Size 139How to Report the Test 140Methods Section 140Results Section 140Discussion Section 141Relevant Videos etc. 141Repeated Measures Analysis of Variance 143When Is the Test Applied? 143An Example 144Presenting the Data 144Numerical Presentation of the Data 145Graphical Presentation of the Data 145Data Requirements 146Variables Required 146Normal Distribution of the Outcome Data 148Equal Standard Deviations 148Equal Sample Sizes 148An Outline of the Test 148Planning Sample Sizes 149Carrying Out the Test 150Describing the Effect Size 150How to Report the Test 151Methods Section 151Results Section 151Discussion Section 152Relevant Videos etc. 153Friedman Test 155When Is the Test Applied? 15516.2An Example 157Presenting the Data 157Bar Charts of the Outcomes at Various Stages 157Summarizing the Data via Medians or Means 157Splitting the Data at Some Critical Point in the Scale 159Data Requirements 160Variables Required 160Normal Distribution and Standard Deviations in the Outcome Data 160Equal Sample Sizes 160An Outline of the Test 160Planning Sample Sizes 161Follow Up Tests 161Carrying Out the Tests 162Describing the Effect Size 162Median or Mean Values Among the Individual Changes 162Split the Scale 162How to Report the Test 162Methods Section 162Results Section 163Discussion Section 164Relevant Videos etc. 164Pearson Correlation 165Presenting the Data 165Correlation Coefficient and Statistical Significance 166Planning Sample Sizes 167Effect Size and Practical Relevance 167Regression 169How to Report the Analysis 170Methods 170Results 170Discussion 171Relevant Videos etc. 171Spearman Correlation 173Presenting the Data 173Testing for Evidence of Inappropriate Distributions 174Rho and Statistical Significance 174An Outline of the Significance Test 175Planning Sample Sizes 175Effect Size 176Where Both Measures Are Ordinal 176Educational Level and Willingness to Undertake Internet Research – An Example Where Both Measures Are Ordinal 176Presenting the Data 177Rho and Statistical Significance 177Effect Size 178How to Report Spearman Correlation Analyses 178Methods 178Results 179Discussion 180Relevant Videos etc. 180Logistic Regression 181Use of Logistic Regression with Categorical Outcomes 181An Outline of the Significance Test 182Planning Sample Sizes 182Results of the Analysis 184Describing the Effect Size 184How to Report the Analysis 185Methods 185Results 186Discussion 186Relevant Videos etc. 187Cronbach’s Alpha 189Appropriate Situations for the Use of Cronbach’s Alpha 18920.2Inappropriate Uses of Alpha 190Interpretation 190Reverse Scoring 191An Example 191Performing and Interpreting the Analysis 192How to Report Cronbach’s Alpha Analyses 193Methods Section 193Results 194Discussion 194Relevant Videos etc. 195Glossary 197Videos 209Index 211Author BiographyAdam Mackridge, Ph.D., is a Research Pharmacist at Betsi Cadwaladr University Health Board in North Wales. He has over 15 years of experience in planning, conducting and reporting health research. He received his PhD in Pharmacy Practice from Aston University in Birmingham, UK.Philip Rowe, Ph.D., is a Visiting Research Fellow in the School of Pharmacy and Molecular Sciences at Liverpool John Moores University, Liverpool, UK. He is a Fellow of the Royal Statistical Society and has authored other statistically based books for Wiley.