Patient-reported outcomes : measurement, implementation and interpretation / Joseph C. Cappelleri [and 5 others].

Format:

Book

Author/Creator:

Cappelleri, Joseph C., author.

Contributor:

EBSCOhost.

President Emeritus Martin Meyerson Fund.

Series:

Chapman & Hall/CRC biostatistics series (Unnumbered)

Chapman & Hall/CRC biostatistics series

Language:

English

Subjects (All):

Medical statistics.

Outcome assessment (Medical care).

Data Interpretation, Statistical.

Outcome Assessment, Health Care.

Health Care Evaluation Mechanisms.

Patient Participation.

Medical Subjects:

Data Interpretation, Statistical.

Outcome Assessment, Health Care.

Health Care Evaluation Mechanisms.

Patient Participation.

Physical Description:

1 online resource (xx, 331 pages) : illustratioons.

Place of Publication:

Boca Raton : CRC Press, [2013]

System Details:

text file

Summary:

Advancing the development, validation, and use of patient-reported outcome (PRO) measures, Patient-Reported Outcomes: Measurement, Implementation and Interpretation helps you develop and enrich your understanding of PRO methodology, particularly from a quantitative perspective. It provides an up-to-date volume on conceptual and analytical issues of PRO measures. The book discusses key concepts relating to the measurement, implementation, and interpretation of PRO measures. It covers both introductory and advanced psychometric and biostatistical methods for constructing and analyzing PRO measures. The authors include many relevant real-life applications based on their extensive first-hand experiences in the pharmaceutical industry. They implement a wealth of simulated datasets to illustrate concepts and heighten understanding based on practical scenarios. For readers interested in conducting statistical analyses of PRO measures and delving more deeply into the analytic details, most chapters contain SAS code and output that illustrate the methodology. Along with providing numerous timely references, the book highlights current regulatory guidelines. Features, Describes how to develop, measure, implement, and interpret PRO measures, Covers key aspects of PRO methodology, including exploratory and confirmatory factor analysis, item response theory, cross-sectional analysis, longitudinal analysis, and mediation models, Highlights recent advances in the assessment of instrument development, reliability, validity, missing data, and multiple testing, Explains how to enhance the interpretation of scores from PRO measures, Illustrates concepts with real-world applications, Provides practical examples with simulated data and analytic implementations using SAS Book jacket.

Contents:

1 Introduction 1

1.1 Patient-Reported Outcomes in Perspective 1

1.2 Patient-Reported Outcomes in Clinical Research 2

1.2.1 Label Claims 4

1.2.2 Beyond Label Claims 5

1.2.3 Clinical Practice 6

1.2.4 Comparative Effectiveness Research 6

1.3 Terms and Definitions 7

1.4 Measurement Scales 7

1.4.1 Properties and Types of Scales 7

1.4.2 Single-Item and Multi-Item Scales 12

1.4.3 Latent Variables and Manifest Variables 12

1.5 Psychometrics versus Clinimetrics 13

1.6 Selection of a PRO Questionnaire 14

1.7 Summary 16

References 16

2 Development of a Patient-Reported Outcome 21

2.1 Population 21

2.2 Item Generation 22

2.2.1 Patient Interviews and Focus Groups 22

2.2.2 Analysis of Qualitative Data 23

2.2.3 Saturation 24

2.3 Item Wording 26

2.4 Cognitive Interviews 26

2.5 Summary 27

References 28

3 Validity 31

3.1 Content Validity 31

3.2 Construct Validity 36

3.2.1 Convergent Validity and Divergent Validity 37

3.2.2 Known-Groups Validity 39

3.2.3 Criterion Validity 41

3.2.3.1 Concurrent Validity 41

3.2.3.2 Predictive Validity 44

3.3 Simulated Example Using SAS: Convergent and Divergent Validity 45

3.4 Factors Affecting Response 47

3.5 Summary 48

References 48

4 Reliability 51

4.1 Intraclass Correlation Coefficient for Continuous Variables 52

4.2 ICC Example 55

4.3 ICC Simulated Example 56

4.4 ICC in Context 58

4.5 Bland and Airman Plot for Continuous Variables 60

4.6 Simple Kappa and Weighted Kappa Coefficients for Categorical Variables 62

4.6.1 Simple Kappa for Binary Data 62

4.6.2 Weighted Kappa for Ordinal Data 63

4.7 Internal Consistency Reliability: Cronbach's Alpha Coefficient 66

4.8 Simulated Example of Cronbach's Alpha 69

4.9 Summary 71

References 71

5 Exploratory and Confirmatory Factor Analyses 75

5.1 Exploratory Factor Analysis 76

5.1.1 Role of Exploratory Factor Analysis 76

5.1.2 EFA Model 77

5.1.3 Number of Factors 78

5.1.4 Factor Rotation 79

5.1.5 Sample Size 79

5.1.6 Assumptions 80

5.2 Confirmatory Factor Analysis 81

5.2.1 Exploratory Factor Analysis versus Confirmatory Factor Analysis 81

5.2.2 Structural and Measurements Models 82

5.2.3 Standard Model versus Nonstandard Model 82

5.2.4 Depicting the Model 82

5.2.5 Identifying Residual Terms for Endogenous Variables 83

5.2.6 Identifying All Parameters to Be Estimated 84

5.2.7 Assessing Fit between Model and Data 84

5.3 Causal Indicators versus Effect Indicators 85

5.4 Simulated Examples Using SAS: Exploratory Factor Analysis 87

5.4.1 Simulated Dataset 87

5.4.2 Implementation 89

5.4.3 Parallel Analysis 92

5.5 Simulated Examples Using SAS: Confirmatory Factor Analysis 92

5.5.1 Simulated Dataset 92

5.5.2 Implementation 95

5.5.3 Nonstandard Measurement Model 99

5.6 Real-Life Examples 103

5.6.1 Minnesota Nicotine Withdrawal Scale 103

5.6.2 Sexual Experience Questionnaire 105

5.6.3 Power of Food Scale 109

5.7 Summary 114

References 115

6 Item Response Theory 117

6.1 Classical Test Theory Revisited 118

6.1.1 Assumptions 118

6.1.2 Item Difficulty, Discrimination, and Weighting 119

6.1.3 CTT and ERT 122

6.2 Assumptions of ERT 122

6.2.1 Unidimensionality 122

6.2.2 Local Independence 123

6.2.3 Model Fit 124

6.3 Item Characteristic Curves 124

6.3.1 Dichotomous Response Models 125

6.3.2 Polytomous Response Models 129

6.4 Item Information 132

6.5 Item Fit and Person Fit 134

6.5.1 Person-Item Maps 134

6.5.2 Fit Indices 137

6.6 Differential Item Functioning 138

6.7 Sample Size 140

6.8 Example 141

6.9 Example: Rasch Model Implementation 143

6.10 Summary 146

References 147

7 Cross-Sectional Analysis 149

7.1 Types of PRO Data and Exploratory Methods 149

7.1.1 Types of PRO Data 149

7.1.2 Exploratory Methods and Descriptive Statistics 151

7.1.3 Simulated Examples Using SAS: Q-Q Plot, Probability Plot, and Normality Test 152

7.2 Comparing Two or More Samples 157

7.2.1 Nonparametric Methods 157

7.2.2 Parametric Methods 158

7.2.3 Simulated Examples Using SAS: t-Test 159

7.3 Regression Analysis 161

7.3.1 Binary Outcome Variable 161

7.3.2 Continuous Outcome Variable 167

7.3.3 Advanced Example: Logistic Regression versus Ordinary Linear Regression 170

7.4 Summary 177

References 177

8 Longitudinal Analysis 181

8.1 Analytic Considerations 182

8.2 Repeated Measures Model 182

8.2.1 Repeated Measures with Time as a Categorical Covariate 183

8.2.2 Implementation of the Repeated Measures Model Using the SAS MIXED Procedure 184

8.2.2.1 Simulated Dataset 184

8.2.2.2 Implementation 186

8.2.3 Covariance Structures 189

8.2.4 Repeated Measures with Time as a Continuous Covariate 191

8.3 Random Coefficient Model 192

8.3.1 Random Intercept-Slope Model 193

8.3.2 Implementation of Random Intercepts and Slopes Model Using SAS MIXED Procedure 195

8.3.2.1 Simulated Dataset 195

8.3.2.2 Implementation 199

8.4 Real-Life Examples 202

8.4.1 Repeated Measures Model 202

8.4.2 Random Coefficient Model 209

8.5 Summary 218

References 218

9 Mediation Models 221

9.1 Single Mediator Model 222

9.1.1 Basics 222

9.1.2 Implementation of the Mediation Model Using the SAS MODEL Procedure 224

9.1.2.1 Simulated Dataset 224

9.1.2.2 Implementation 227

9.1.3 Example with Multiple Independent Variables 230

9.1.3.1 Simulated Dataset 231

9.1.3.2 Implementation 232

9.2 Model Invariance 235

9.2.1 Group Invariance 238

9.2.2 Longitudinal Mediation Models and Time Invariance 240

9.2.2.1 Simulated Dataset 244

9.2.2.2 Implementation 247

9.3 Advanced Example 248

9.3.1 Background 248

9.3.2 Mediation Model and Analysis 251

9.4 Bootstrapping Methodology Implementation 252

9.5 Summary 259

References 259

10 Missing Data 261

10.1 Study Design to Minimize Missing Data 262

10.2 Missing Data Patterns and Mechanisms 264

10.2.1 Missing Completely at Random 264

10.2.2 Missing at Random 265

10.2.3 Missing Not at Random 266

10.3 Approaches for Missing Items within Domains or Measures 268

10.4 Approaches for Missing Entire Domains or Entire Questionnaires 270

10.4.1 Complete Case Analysis 270

10.4.2 Imputation 271

10.4.3 Maximum Likelihood Methods 272

10.4.4 MNAR Models 272

10.5 Sensitivity Analyses 274

10.6 Simulated Example Using SAS: Pattern Mixture Models 275

10.7 Summary 283

References 284

11 Enriching Interpretation 287

11.1 Anchor-Based Approaches 288

11.1.1 Percentages Based on Thresholds 288

11.1.2 Simulated Example: Severity Categorization 291

11.1.3 Criterion-Group Interpretation 293

11.1.4 Content-Based Interpretation 297

11.1.5 Clinically Important Difference 299

11.1.6 Simulated Example: Clinically Important Difference 301

11.2 Distribution-Based Approaches 307

11.2.1 Effect Size 309

11.2.2 Probability of Relative Benefit 311

11.2.3 Responder Analysis and Cumulative Proportions 312

11.2.4 Simulated Example: CDF Plots 314

11.3 Multiple Testing 316

11.4 Summary 318

Acknowledgment 318

References 318.

Notes:

Includes bibliographical references and index.

Electronic reproduction. Ipswich, MA Available via World Wide Web.

Description based on online resource; title from digital title page (viewed on Mar. 3, 2014).

Local Notes:

Acquired for the Penn Libraries with assistance from the President Emeritus Martin Meyerson Fund.

Other Format:

Print version: Cappelleri, Joseph C. Patient-reported outcomes.

ISBN:

9781439873700

1439873704

Publisher Number:

99957526503

Access Restriction:

Restricted for use by site license.