Book contents
- Multiverse Analysis
- Analytical Methods for Social Research
- Multiverse Analysis
- Copyright page
- Contents
- Figures
- Tables
- Acknowledgments
- Part I Introduction
- Part II The Computational Multiverse
- 3 Hurricane Names
- 4 The Multiverse Algorithm
- 5 Empirical Multiverses
- 6 Influence Analysis and Scope Conditions
- 7 Good and Bad Controls
- 8 Some Alternative Approaches
- Part III Expanding the Multiverse
- Appendix: Coding with MULTIVRS in Stata
- References
- Index
7 - Good and Bad Controls
from Part II - The Computational Multiverse
Published online by Cambridge University Press: 28 February 2025
Book contents
- Multiverse Analysis
- Analytical Methods for Social Research
- Multiverse Analysis
- Copyright page
- Contents
- Figures
- Tables
- Acknowledgments
- Part I Introduction
- Part II The Computational Multiverse
- 3 Hurricane Names
- 4 The Multiverse Algorithm
- 5 Empirical Multiverses
- 6 Influence Analysis and Scope Conditions
- 7 Good and Bad Controls
- 8 Some Alternative Approaches
- Part III Expanding the Multiverse
- Appendix: Coding with MULTIVRS in Stata
- References
- Index
Summary
Control variable strategies can go wrong and controls can make estimates worse rather than better. In this chapter, we discuss why control variables always deserve skepticism and require specific justification. We discuss criteria for plausible controls, bad controls, and why one should not control for everything we can measure (aka kitchen sink models). There are common conditions in which controlling for a variable causes bias, and therefore when excluding that control variable reduces bias.
Keywords
- Type
- Chapter
- Information
- Multiverse AnalysisComputational Methods for Robust Results, pp. 98 - 114Publisher: Cambridge University PressPrint publication year: 2025