Testing Missing At Random Using Instrumental Variables

Arbeitspapier

This paper proposes a test for missing at random (MAR). The MAR assumption is shown to be testable given instrumental variables which are independent of response given potential outcomes. A nonparametric testing procedure based on integrated squared distance is proposed. The statistic\'s asymptotic distribution under the MAR hypothesis is derived. In particular, our results can be applied to testing missing completely at random (MCAR). A Monte Carlo study examines finite sample performance of our test statistic. An empirical illustration analyzes the nonresponse mechanism in labor income questions.

Object Details

• Language: Englisch

References and Relationships

• Bibliographic citation: Series: Discussion Paper ; No. 59

Classification and Topics

• Classification: Wirtschaft ; Hypothesis Testing: General ; Semiparametric and Nonparametric Methods: General
• Subject: incomplete data ; missing-data mechanism ; selection model ; nonparametric hypothesis testing ; consistent testing ; instrumental variable ; series estimation

Contributors, Places and Time

• Event: Geistige Schöpfung
• (who): Breunig, Christoph
• Event: Veröffentlichung
• (who): Ludwig-Maximilians-Universität München und Humboldt-Universität zu Berlin, Collaborative Research Center Transregio 190 - Rationality and Competition
• (where): München und Berlin
• (when): 2017

Further information

• Handle: http://hdl.handle.net/10419/185729
• Last update: 10.03.2025, 11:45 AM CET