| |
| |
Preface | |
| |
| |
| |
The First Rule: There Should Be the Possibility of Surprise in Social Research | |
| |
| |
Selecting a Research Question | |
| |
| |
Researchable Questions | |
| |
| |
Interesting Questions | |
| |
| |
Selecting a Sample | |
| |
| |
Samples in Qualitative Studies | |
| |
| |
Is Meaningful Social Research Possible? | |
| |
| |
Summary | |
| |
| |
Student Exercises on Rule 1 | |
| |
| |
| |
The Second Rule: Look for Differences That Make a Difference, and Report Them | |
| |
| |
You Can't Explain a Variable with a Constant | |
| |
| |
Maximizing Variance to Find the Effect of a Cause | |
| |
| |
Size versus Statistical Significance | |
| |
| |
Comparing Effects Where There Is a Common Metric | |
| |
| |
Calibration: Converting Explanatory Variables to a Common Metric | |
| |
| |
Substantive Profiling: The Use of Telling Comparisons | |
| |
| |
Visual Presentation of Results | |
| |
| |
Policy Importance | |
| |
| |
Importance for Theory | |
| |
| |
Conclusion | |
| |
| |
Student Exercises on Rule 2 | |
| |
| |
| |
The Third Rule: Build Reality Checks into Your Research | |
| |
| |
Internal Reality Checks | |
| |
| |
Reality Checks on Data-Dubious Values and Incomplete Data | |
| |
| |
Reality Checks on Measures-Aim for Consistency in Conceptualization and Measurement | |
| |
| |
Reality Checks on Models-The Formal Equivalence Check | |
| |
| |
External Reality Checks: Validation with Other Data and Methods | |
| |
| |
Using Causal-Process Observations to Test Plausibility of Results | |
| |
| |
Using Ethnographic Data to Help Interpret Survey Results | |
| |
| |
Other Examples of Multiple-Method Research | |
| |
| |
Concluding Remark | |
| |
| |
Student Exercises on Rule 3 | |
| |
| |
| |
The Fourth Rule: Replicate Where Possible | |
| |
| |
Sources of Uncertainty in Social Research | |
| |
| |
Overview: From Population to Sample and Back to Population | |
| |
| |
Measurement Error as a Source of Uncertainty | |
| |
| |
Illustration: Two Methods for Estimating Global Poverty | |
| |
| |
Toward a Solution: Identical Analyses of Parallel Data Sets | |
| |
| |
Meta-analysis: Synthesizing Results Formally across Studies | |
| |
| |
Summary: Your Confidence Intervals Are Too Narrow | |
| |
| |
Student Exercises on Rule 4 | |
| |
| |
| |
The Fifth Rule: Compare Like with Like | |
| |
| |
Correlation and Causality | |
| |
| |
Types of Strategies for Comparing Like with Like | |
| |
| |
Matching versus Looking for Differences | |
| |
| |
The Standard Regression Method for Comparing Like with Like | |
| |
| |
Critique of the Standard Linear Regression Strategy | |
| |
| |
Comparing Like with Like Through Fixed-Effects Methods | |
| |
| |
First-Difference Models: Subtracting Out the Effects of Confounding Variables | |
| |
| |
Special Case: Growth-Rate Models | |
| |
| |
Sibling Models | |
| |
| |
Comparing Like with Like through Matching on Measured Variables | |
| |
| |
Exact Matching | |
| |
| |
Propensity-Score Method | |
| |
| |
Matching as a Preprocessing Strategy for Reducing Model Dependence | |
| |
| |
Comparing Like with Like through Naturally Occurring Random Assignment | |
| |
| |
Instrumental Variables: Matching through Partial Random Assignment | |
| |
| |
Matching Through Naturally Occurring Random Assignment to the Treatment Group | |
| |
| |
Comparison of Strategies for Comparing Like with Like | |
| |
| |
Conclusion | |
| |
| |
Student Exercises on Rule 5 | |
| |
| |
| |
The Sixth Rule: Use Panel Data to Study Individual Change and Repeated Cross-section Data to Study Social Change | |
| |
| |
Analytic Differences between Panel and Repeated Cross-section Data | |
| |
| |
Three General Questions about Change | |
| |
| |
Changing-Effect Models, Part 1: Two Points in Time | |
| |
| |
Changing-Effect Models, Part 2: Multilevel Models with Time as the Context | |
| |
| |
What We Want to Know | |
| |
| |
The General Multilevel Model | |
| |
| |
Convergence Models | |
| |
| |
The Sign Test for Convergence: Comparing Your [phi]s and [delta]s | |
| |
| |
Convergence Model versus Changing-Effect Model | |
| |
| |
Bridging Individual and Social Change: Estimating Cohort Replacement Effects | |
| |
| |
An Accounting Scheme for Social Change | |
| |
| |
Linear Decomposition Method | |
| |
| |
Summary | |
| |
| |
Student Exercises on Rule 6 | |
| |
| |
| |
The Seventh Rule: Let Method Be the Servant, Not the Master | |
| |
| |
Obsession with Regression | |
| |
| |
Naturally Occurring Random Assignment, Again | |
| |
| |
Decomposition Work in the Social Sciences | |
| |
| |
Decomposition of Variance and Inequality | |
| |
| |
Decomposition of Segregation Indexes | |
| |
| |
The Effects of Social Context | |
| |
| |
Context Effects as Objects of Study | |
| |
| |
Context Effects as Nuisance | |
| |
| |
Critical Tests in Social Research | |
| |
| |
Conclusion | |
| |
| |
Student Exercises on Rule 7 | |
| |
| |
References | |
| |
| |
Index | |