Enhanced descriptions from Syndetics:

In the Fourth Edition of Scale Development, Robert F. DeVellis demystifies measurement by emphasizing a logical rather than strictly mathematical understanding of concepts. The text supports readers in comprehending newer approaches to measurement, comparing them to classical approaches, and grasping more clearly the relative merits of each. This edition addresses new topics pertinent to modern measurement approaches and includes additional exercises and topics for class discussion.

Table of contents provided by Syndetics

• Preface (p. xiii)
• About the Author (p. xvii)
• Chapter 1 Overview (p. 1)
• General Perspectives on Measurement (p. 2)
• Historical Origins of Measurement in Social Science (p. 4)
• Early Examples (p. 4)
• Emergence of Statistical Methods and the Role of Mental Testing (p. 6)
• The Role of Psychophysics (p. 6)
• Later Developments in Measurement (p. 7)
• Evolution of Basic Concepts (p. 7)
• Evolution of Mental Testing (p. 8)
• Assessment of Mental Illness (p. 8)
• Broadening the Domain of Psychometrics (p. 12)
• The Role of Measurement in the Social Sciences (p. 13)
• The Relationship of Theory to Measurement (p. 13)
• Theoretical and Atheoretical Measures (p. 14)
• Measurement Scales (p. 15)
• All Scales Are Not Created Equal (p. 17)
• Costs of Poor Measurement (p. 19)
• Summary and Preview (p. 20)
• Exercises (p. 21)
• Chapter 2 Understanding the Latent Variable (p. 23)
• Constructs Versus Measures (p. 23)
• Latent Variable as the Presumed Cause of Item Values Path Diagrams (p. 26)
• Diagrammatic Conventions (p. 26)
• Path Diagrams in Scale Development (p. 27)
• Further Elaboration of the Measurement Model (p. 29)
• Classical Measurement Assumptions (p. 29)
• Parallel Tests (p. 30)
• Alternative Models (p. 33)
• Choosing a Causal Model (p. 36)
• Exercises (p. 37)
• Note (p. 37)
• Chapter 3 Reliability (p. 39)
• Methods Based on the Analysis of Variance (p. 40)
• Continuous Verstis Dichotomous Items (p. 42)
• Internal Consistency (p. 42)
• Coefficient Alpha (p. 43)
• The Covariance Matrix (p. 44)
• Covariance Matrices for Multi-Item Scales (p. 45)
• Alpha and the Covariance Matrix (p. 46)
• Alternative Formula for Alpha (p. 50)
• Critique of Alpha (p. 52)
• Remedies to Alpha's Limitations (p. 57)
• Coefficient Omega (¿) (p. 59)
• Reliability Based on Correlations Between Scale Scores (p. 61)
• Alternate-Forms Reliability (p. 61)
• Split-Half Reliability (p. 62)
• Inter-Rater Agreement (p. 66)
• Temporal Stability (p. 67)
• Reliability of Change Scores (p. 70)
• Reliability and Statistical Power (p. 76)
• Generalizability Theory (p. 77)
• Summary (p. 80)
• Exercises (p. 81)
• Notes (p. 82)
• Chapter 4 Validity (p. 83)
• Content Validity (p. 84)
• Scope of the Variable and Implications for Content Validity (p. 85)
• Criterion-Related Validity (p. 92)
• Criterion-Related Validity Versus Accuracy (p. 92)
• Construct Validity (p. 95)
• Differentiating Construct From Criterion-Related Validity (p. 95)
• Attenuation (p. 97)
• How Strong Should Correlations Be to Demonstrate Construct Validity? (p. 98)
• Multitrait-Multimethod Matrix (p. 98)
• What About Face Validity? (p. 100)
• Exercises (p. 103)
• Chapter 5 Guidelines in Scale Development (p. 105)
• Step 1 Determine Clearly What It Is You Want to Measure (p. 105)
• Theory as an Aid to Clarity (p. 105)
• Specificity as an Aid to Clarity (p. 106)
• Being Clear About What to Include in a Measure (p. 108)
• Step 2 Generate an Item Pool (p. 109)
• Choose Items That Reflect the Scale's Purpose (p. 109)
• Redundancy (p. 110)
• Number of Items (p. 113)
• Beginning the Process of Writing Items (p. 113)
• Characteristics of Good and Bad Items (p. 114)
• Positively and Negatively Worded Items (p. 116)
• Conclusion (p. 118)
• Step 3 Determine the Format for Measurement (p. 118)
• Thurstone Scaling (p. 119)
• Guttman Scaling (p. 120)
• Scales With Equally Weighted Items (p. 122)
• How Many Response Categories? (p. 122)
• Specific Types of Response Formats (p. 126)
• Likert Scale (p. 127)
• Semantic Differential (p. 129)
• Visual Analog (p. 130)
• Numerical Response Formats and Basic Neural Processes (p. 132)
• Binary Options (p. 133)
• Item Time Frames (p. 134)
• Step 4 Have Initial Item Pool Reviewed by Experts (p. 134)
• Step 5 Consider Inclusion of Validation Items (p. 136)
• Step 6 Administer Items to a Development Sample (p. 137)
• Step 7 Evaluate the Items (p. 139)
• Initial Examination of Items' Performance (p. 140)
• Reverse Scoring (p. 140)
• Item-Scale Correlations (p. 142)
• Item Variances (p. 142)
• Item Means (p. 143)
• Dimensionality (p. 143)
• Reliability (p. 144)
• Step 8 Optimize Scale Length (p. 146)
• Effect of Scale Length on Reliability (p. 146)
• Effects of Dropping "Bad" Items (p. 147)
• Tinkering With Scale length (p. 148)
• Split Samples (p. 149)
• Exercises (p. 150)
• Note (p. 151)
• Chapter 6 Factor Analysis (p. 153)
• Overview of Factor Analysis (p. 155)
• Examples of Methods Analogous to Factor Analytic Concepts (p. 156)
• Example 1 (p. 156)
• Example 2 (p. 157)
• Shortcomings of These Methods (p. 158)
• Conceptual Description of Factor Analysis (p. 161)
• Extracting Factors (p. 161)
• The First Factor (p. 161)
• Subsequent Factors (p. 164)
• Deciding How Many Factors to Extract (p. 165)
• Rotating Factors (p. 171)
• Rotation Analogy 1 (p. 172)
• Rotation Analogy 2 (p. 172)
• Rotation Analogy 3 (p. 175)
• Orthogonal Versus Oblique Rotation (p. 180)
• Choosing Type of Rotation (p. 184)
• Bifactor and Hierarchical Factor Models (p. 185)
• Interpreting Factors (p. 192)
• Principal Components Versus Common Factors (p. 193)
• Same or Different? (p. 194)
• Confirmatory Factor Analysis (p. 197)
• Using Factor Analysis in Scale Development (p. 199)
• Sample Size (p. 203)
• Conclusion (p. 204)
• Exercises (p. 204)
• Chapter 7 An Overview of Item Response Theory (p. 205)
• Item Difficulty (p. 209)
• Item Discrimination (p. 210)
• Guessing, or False Positives (p. 211)
• Item-Characteristic Curves (p. 213)
• IRT Applied to Multiresponse Items (p. 217)
• Theta and Computerized Adaptive Testing (CAT) (p. 224)
• Complexities of IRT (p. 226)
• Conclusions (p. 229)
• Exercises (p. 231)
• Chapter 8 Measurement in the Broader Research Context (p. 233)
• Before Scale Development (p. 233)
• Look for Existing Tools (p. 233)
• View the Construct in the Context of the Population of Interest (p. 235)
• Decide on the Mode of Scale Administration (p. 237)
• Consider the Scale in the Context of Other Measures or Procedures (p. 237)
• After Scale Administration (p. 239)
• Analytic Issues (p. 239)
• Interpretation Issues (p. 239)
• Generalizability (p. 240)
• Final Thoughts (p. 240)
• Small Measurement and Big Measurement (p. 240)
• Canoes and Cruise Ships (p. 240)
• Measurement "Canoes" and Measurement "Cruise Ships" (p. 242)
• Practical Implications of Small Versus Big Measurement (p. 244)
• Remember, Measurement Matters (p. 246)
• Exercise (p. 246)
• References (p. 247)
• Index (p. 257)