| |
| |
Preface | |
| |
| |
About the Editors | |
| |
| |
Acknowledgments | |
| |
| |
Introduction | |
| |
| |
| |
Statistical Issues | |
| |
| |
| |
Missing Data Techniques and Low Response Rates: The Role of Systematic Nonresponse Parameters | |
| |
| |
| |
Organization of the Chapter | |
| |
| |
Levels, Problems, and Mechanisms of Missing Data | |
| |
| |
Three Levels of Missing Data | |
| |
| |
Two Problems Caused by Missing Data (External Validity and Statistical Power) | |
| |
| |
Missingness Mechanisms (MCAR, MAR, and MNAR) | |
| |
| |
Missing Data Treatments | |
| |
| |
A Fundamental Principle of Missing Data Analysis | |
| |
| |
Missing Data Techniques (Listwise and Pairwise Deletion, ML, and MI) | |
| |
| |
Systematic Nonresponse Parameters (d[subscript miss] and f[superscript 2 subscript miss]) | |
| |
| |
Theory of Survey Nonresponse | |
| |
| |
Missing Data Legends | |
| |
| |
| |
"Low Response Rates Invalidate Results" | |
| |
| |
| |
"When in Doubt, Use Listwise or Pairwise Deletion" | |
| |
| |
Applications | |
| |
| |
Longitudinal Modeling | |
| |
| |
Within-Group Agreement Estimation | |
| |
| |
Meta-analysis | |
| |
| |
Social Network Analysis | |
| |
| |
Moderated Regression | |
| |
| |
Conclusions | |
| |
| |
Future Research on d[subscript miss] and f[superscript 2 subscript miss] | |
| |
| |
Missing Data Techniques | |
| |
| |
References | |
| |
| |
Appendix | |
| |
| |
Derivation of Response Rate Bias for the Correlation (Used to Generate Figure 1.1c) | |
| |
| |
| |
The Partial Revival of a Dead Horse? Comparing Classical Test Theory and Item Response Theory | |
| |
| |
| |
Basic Statement of the Two Theories | |
| |
| |
Classical Test Theory | |
| |
| |
Item Response Theory | |
| |
| |
Criticisms and Limitations of CTT | |
| |
| |
Lack of Population Invariance | |
| |
| |
Person and Item Parameters on Different Scales | |
| |
| |
Correlations Between Item Parameters | |
| |
| |
Reliability as a Monolithic Concept | |
| |
| |
Criticisms and Limitations of IRT | |
| |
| |
Large Sample Sizes | |
| |
| |
Strong Assumptions | |
| |
| |
Complicated Programs | |
| |
| |
Times to Use CTT | |
| |
| |
Small Sample Sizes | |
| |
| |
Multidimensional Data? | |
| |
| |
CTT Supports Other Methodologies | |
| |
| |
Times to Use IRT | |
| |
| |
Focus on Particular Range of Construct | |
| |
| |
Conduct Goodness-of-Fit Studies | |
| |
| |
IRT Supports Many Psychometric Tools | |
| |
| |
Conclusions | |
| |
| |
References | |
| |
| |
| |
Four Common Misconceptions in Exploratory Factor Analysis | |
| |
| |
| |
The Choice Between Component and Common Factor Analysis Is Inconsequential | |
| |
| |
The Component Versus Common Factor Debate: Methodological Arguments | |
| |
| |
The Component Versus Common Factor Debate: Philosophical Arguments | |
| |
| |
Differences in Results from Component and Common Factor Analysis | |
| |
| |
Orthogonal Rotation Results in Better Simple Structure Than Oblique Rotation | |
| |
| |
Oblique or Orthogonal Rotation? | |
| |
| |
Do Orthogonal Rotations Result in Better Simple Structure? | |
| |
| |
The Minimum Sample Size Needed for Factor Analysis Is... (Insert Your Favorite Guideline) | |
| |
| |
New Sample Size Guidelines | |
| |
| |
The "Eigenvalues Greater Than One" Rule Is the Best Way of Choosing the Number of Factors | |
| |
| |
Discussion | |
| |
| |
References | |
| |
| |
| |
Dr. StrangeLOVE, or: How I Learned to Stop Worrying and Love Omitted Variables | |
| |
| |
| |
Theoretical and Mathematical Definition of the Omitted Variables Problem | |
| |
| |
Violated Assumptions | |
| |
| |
More Complex Models | |
| |
| |
Path Coefficient Bias Versus Significance Testing | |
| |
| |
Minimizing the Risk of LOVE | |
| |
| |
Experimental Control | |
| |
| |
More Inclusive Models | |
| |
| |
Use Previous Research to Justify Assumptions | |
| |
| |
Consideration of Research Purpose | |
| |
| |
References | |
| |
| |
| |
The Truth(s) on Testing for Mediation in the Social and Organizational Sciences | |
| |
| |
| |
Baron and Kenny's (1986) Four-Step Test of Mediation | |
| |
| |
Condition/Step 1 | |
| |
| |
Condition/Step 2 | |
| |
| |
Condition/Step 3 | |
| |
| |
Condition/Step 4 | |
| |
| |
The Urban Legend: Baron and Kenny's Four-Step Test Is an Optimal and Sufficient Test for Mediation Hypotheses | |
| |
| |
The Kernel of Truth About the Urban Legends | |
| |
| |
Debunking the Legends | |
| |
| |
| |
A Test of a Mediation Hypothesis Should Consist of the Four Steps Articulated by Baron and Kenny (1986) | |
| |
| |
| |
Baron and Kenny's (1986) Four-Step Procedure Is the Optimal Test of Mediation Hypotheses | |
| |
| |
| |
Fulfilling the Conditions Articulated in the Baron and Kenny (1986) Four-Step Test Is Sufficient for Drawing Conclusions About Mediated Relationships | |
| |
| |
Suggestions for Testing Mediation Hypotheses | |
| |
| |
Structural Equation Modeling (SEM) as an Analytic Framework | |
| |
| |
Summary of Tests of Mediation | |
| |
| |
A Heuristic Framework for Classifying Mediation Models | |
| |
| |
Summary | |
| |
| |
Conclusion | |
| |
| |
Author Note | |
| |
| |
References | |
| |
| |
| |
Seven Deadly Myths of Testing Moderation in Organizational Research | |
| |
| |
| |
The Seven Myths | |
| |
| |
| |
Product Terms Create Multicollinearity Problems | |
| |
| |
| |
Coefficients on First-Order Terms Are Meaningless | |
| |
| |
| |
Measurement Error Poses Little Concern When First-Order Terms Are Reliable | |
| |
| |
| |
Product Terms Should Be Tested Hierarchically | |
| |
| |
| |
Curvilinearity Can Be Disregarded When Testing Moderation | |
| |
| |
| |
Product Terms Can Be Treated as Causal Variables | |
| |
| |
| |
Testing Moderation in Structural Equation Modeling Is Impractical | |
| |
| |
Myths Beyond Moderation | |
| |
| |
Conclusion | |
| |
| |
References | |
| |
| |
| |
Alternative Model Specifications in Structural Equation Modeling: Facts, Fictions, and Truth | |
| |
| |
| |
The Core of the Issue | |
| |
| |
AMS Strategies | |
| |
| |
Equivalent Models | |
| |
| |
Nested Models | |
| |
| |
Nonnested Alternative Models | |
| |
| |
Summary | |
| |
| |
AMS in Practice | |
| |
| |
Summary | |
| |
| |
References | |
| |
| |
| |
On the Practice of Allowing Correlated Residuals Among Indicators in Structural Equation Models | |
| |
| |
| |
Unraveling the Urban Legend | |
| |
| |
Extent of the Problem | |
| |
| |
Origins | |
| |
| |
A Brief Review of Structural Equation Modeling | |
| |
| |
Indicator Residuals | |
| |
| |
Model Fit | |
| |
| |
An Example | |
| |
| |
Why Correlated IRs Improve Fit | |
| |
| |
Problems With Correlated Residuals | |
| |
| |
Recommendations | |
| |
| |
Summary and Conclusions | |
| |
| |
References | |
| |
| |
| |
Methodological Issues | |
| |
| |
| |
Qualitative Research: The Redheaded Stepchild in Organizational and Social Science Research? | |
| |
| |
| |
Definitional Issues | |
| |
| |
Philosophical Differences in Qualitative and Quantiative Research | |
| |
| |
Quantitative and Qualitative Conceptualizations of Validity | |
| |
| |
Caveats and Assumptions | |
| |
| |
Beliefs Associated With Qualitative Research | |
| |
| |
| |
Qualitative Research Does Not Utilize the Scientific Method | |
| |
| |
| |
Qualitative Research Lacks Methodological Rigor | |
| |
| |
| |
Qualitative Research Contributes Little to the Advancement of Knowledge | |
| |
| |
Evaluating the Beliefs Associated With Qualitative Research | |
| |
| |
| |
Qualitative Research Does Not Utilize the Scientific Method | |
| |
| |
| |
Qualitative Research Is Methodologically Weak | |
| |
| |
| |
Qualitative Research Has Weak Internal Validity | |
| |
| |
| |
Qualitative Research Has Weak Construct Validity | |
| |
| |
| |
Qualitative Research Has Weak External Validity | |
| |
| |
| |
Qualitative Research Contributes Little to the Advancement of Knowledge | |
| |
| |
The Future of Qualitative Research in the Social and Organizational Sciences | |
| |
| |
Concluding Thoughts | |
| |
| |
Author Note | |
| |
| |
References | |
| |
| |
| |
Do Samples Really Matter That Much? | |
| |
| |
| |
Kernel of Truth | |
| |
| |
Background | |
| |
| |
History of the Concern | |
| |
| |
The Research Base | |
| |
| |
Why Do Samples Seem to Matter So Much? | |
| |
| |
People Confuse Random Sampling With Random Assignment | |
| |
| |
People Focus on the Wrong Things | |
| |
| |
People Rely on Superficial Similarities | |
| |
| |
Concluding Thoughts | |
| |
| |
Author Note | |
| |
| |
References | |
| |
| |
| |
Sample Size Rules of Thumb: Evaluating Three Common Practices | |
| |
| |
| |
Determine Whether Sample Size Is Appropriate by Conducting a Power Analysis Using Cohen's Definitions of Small, Medium, and Large Effect Size | |
| |
| |
Discussion | |
| |
| |
Increase the A Priori Type I Error Rate to .10 Because of Your Small Sample Size | |
| |
| |
Discussion | |
| |
| |
Sample Size Should Include at Least 5 Observations per Estimated Parameter in Covariance Structure Analyses | |
| |
| |
Discussion | |
| |
| |
Discussion | |
| |
| |
Author Note | |
| |
| |
References | |
| |
| |
| |
When Small Effect Sizes Tell a Big Story, and When Large Effect Sizes Don't | |
| |
| |
| |
Effect Size Defined | |
| |
| |
The Urban Legend | |
| |
| |
The Kernel of Truth | |
| |
| |
Quine and Ontological Relativism | |
| |
| |
Contextualization | |
| |
| |
Inauspicious Designs | |
| |
| |
Phenomena With Obscured Consequences | |
| |
| |
Phenomena That Challenge Fundamental Assumptions | |
| |
| |
The Flip Side: Trivial "Large" Effects | |
| |
| |
Conclusion | |
| |
| |
References | |
| |
| |
| |
So Why Ask Me? Are Self-Report Data Really That Bad? | |
| |
| |
| |
The Urban Legend of Self-Report Data and Its Historical Roots | |
| |
| |
| |
Construct Validity of Self-Report Data | |
| |
| |
| |
Interpreting the Correlations in Self-Report Data | |
| |
| |
| |
Social Desirability Responding in Self-Report Data | |
| |
| |
| |
Value of Data Collected From Non-Self-Report Measures | |
| |
| |
Conclusion and Moving Forward | |
| |
| |
References | |
| |
| |
| |
If It Ain't Trait It Must Be Method: (Mis)application of the Multitrait-Multimethod Design in Organizational Research | |
| |
| |
| |
Background | |
| |
| |
Literature Review | |
| |
| |
Range of Traits Studied | |
| |
| |
Range of Methods Studied | |
| |
| |
Not All "Measurement Methods" Are Created Equal | |
| |
| |
The Case of Multisource Performance Appraisal | |
| |
| |
The Case of AC Construct Validity | |
| |
| |
Other Cases | |
| |
| |
So, Are Any "Method" Facets Really Method Facets? | |
| |
| |
Discriminating Method From Substance, or "If It Looks Like a Method and Quacks Like a Method..." | |
| |
| |
References | |
| |
| |
| |
Chopped Liver? OK. Chopped Data? Not OK | |
| |
| |
| |
Urban Legends Regarding Chopped Data | |
| |
| |
Urban Legends Associated With the Occurrence of Chopped Data | |
| |
| |
Urban Legends Associated With Chopped Data Techniques | |
| |
| |
Urban Legends Associated With Chopped Data Justifications | |
| |
| |
Literature Review | |
| |
| |
Chopped Data Through the Years | |
| |
| |
Prevalence of Chopped Data | |
| |
| |
The Occurrence of Chopped Data Over Time | |
| |
| |
Chopped Data Across Disciplines | |
| |
| |
Types of Chopped Data Approaches | |
| |
| |
Evaluating Justifications for Using Chopped Data | |
| |
| |
Insufficient or Faulty Justifications (Myths) | |
| |
| |
Legitimate Justifications (Truths) | |
| |
| |
Advantages of, Disadvantages of, and Recommendations for Using Chopped Data | |
| |
| |
(Perceived) Advantages of Chopping Data | |
| |
| |
Disadvantages of Chopping Data | |
| |
| |
Recommendations When Faced With Chopping Data | |
| |
| |
Conclusion | |
| |
| |
References | |
| |
| |
Subject Index | |
| |
| |
Author Index | |