Bootstrap Inference in a Linear Equation Estimated by Instrumental Variables

Arbeitspapier

We study several tests for the coefficient of the single right-hand-side endogenous variable in a linear equation estimated by instrumental variables. We show that all the test statistics--Student's t, Anderson-Rubin, Kleibergen's K, and likelihood ratio (LR)--can be written as functions of six random quantities. This leads to a number of interesting results about the properties of the tests under weak-instrument asymptotics. We then propose several new procedures for bootstrapping the three non-exact test statistics and a conditional version of the LR test. These use more efficient estimates of the parameters of the reduced-form equation than existing procedures. When the best of these new procedures is used, K and conditional LR have excellent performance under the null, and LR also performs very well. However, power considerations suggest that the conditional LR test, bootstrapped using this new procedure when the sample size is not large, is probably the method of choice.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: Queen's Economics Department Working Paper ; No. 1024

Classification and Topics

• Classification: Wirtschaft ; Hypothesis Testing: General ; Statistical Simulation Methods: General ; Multiple or Simultaneous Equation Models; Multiple Variables: General
• Subject: bootstrap test ; weak instruments ; anderson-rubin test ; conditional LR test ; wald test ; instrumental variables ; Bootstrap-Verfahren ; Statistische Methode

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Davidson, Russell ; MacKinnon, James G.
• Event: Veröffentlichung
• (who): Queen's University, Department of Economics
• (where): Kingston (Ontario)
• (when): 2006

Further information

• Handle: http://hdl.handle.net/10419/189308
• Last update: 10.03.2025, 11:43 AM CET