Let the Data Speak? On the Importance of Theory-Based Instrumental Variable Estimations

Arbeitspapier

In absence of randomized controlled experiments, identification is often aimed via instrumental variable (IV) strategies, typically two-stage least squares estimations. According to Bayes’ rule, however, under a low ex ante probability that a hypothesis is true (e.g. that an excluded instrument is partially correlated with an endogenous regressor), the interpretation of the estimation results may be fundamentally flawed. This paper argues that rigorous theoretical reasoning is key to design credible identification strategies, aforemost finding candidates for valid instruments. We discuss prominent IV analyses from the macro-development literature to illustrate the potential benefit of structurally derived IV approaches.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: CESifo Working Paper ; No. 7469

Classification and Topics

• Classification: Wirtschaft ; Econometric and Statistical Methods and Methodology: General ; Multiple or Simultaneous Equation Models: Instrumental Variables (IV) Estimation ; Macroeconomic Analyses of Economic Development
• Subject: Bayes’ rule ; economic development ; identification ; instrumental variable estimation ; macroeconomic theory

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Grossmann, Volker ; Osikominu, Aderonke
• Event: Veröffentlichung
• (who): Center for Economic Studies and ifo Institute (CESifo)
• (where): Munich
• (when): 2019

Further information

• Handle: http://hdl.handle.net/10419/198829
• Last update: 10.03.2025, 11:42 AM CET