Arbeitspapier

Testing missing at random using instrumental variables

to connected objects

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.

Language
Englisch

Bibliographic citation
Series: SFB 649 Discussion Paper ; No. 2017-007

Classification
Wirtschaft
Subject
incomplete data
missing-data mechanism
selection model
nonparametric hypothesis testing
consistent testing
instrumental variable
series estimation

Event
Geistige Schöpfung
(who)
Breunig, Christoph
Event
Veröffentlichung
(who)
Humboldt University of Berlin, Collaborative Research Center 649 - Economic Risk
(where)
Berlin
(when)
2017

Handle
Last update
10.03.2025, 11:41 AM CET

Data provider

This object is provided by:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.
Show original at data provider

Object type

  • Arbeitspapier

Associated

  • Breunig, Christoph
  • Humboldt University of Berlin, Collaborative Research Center 649 - Economic Risk

Time of origin

  • 2017

Other Objects (12)

Testing Missing At Random Using Instrumental Variables

Arbeitspapier

Testing Missing At Random Using Instrumental Variables

Testing missing at random using instrumental variables

Arbeitspapier

Testing missing at random using instrumental variables

Testing Missing at Random using Instrumental Variables

Testing Missing at Random using Instrumental Variables

Testing Missing at Random using Instrumental Variables

Testing Missing at Random using Instrumental Variables

Instrumental variables estimation with partially missing instruments

Instrumental variables estimation with partially missing instruments

Instrumental variables estimation with partially missing instruments

Arbeitspapier

Instrumental variables estimation with partially missing instruments

An instrumental variable random coefficients model for binary outcomes

Arbeitspapier

An instrumental variable random coefficients model for binary outcomes

Causal random forests model using instrumental variable quantile regression

Artikel

Causal random forests model using instrumental variable quantile regression

Instrumental variables estimation of a generalized correlated random coefficients model

Arbeitspapier

Instrumental variables estimation of a generalized correlated random coefficients model

Estimating and testing non-linear models using instrumental variables

Arbeitspapier

Estimating and testing non-linear models using instrumental variables

Instrumental variables, local instrumental variables and control functions

Arbeitspapier

Instrumental variables, local instrumental variables and control functions

Pivotal Statistics for Testing Structural Parameters in Instrumental Variables Regression

Arbeitspapier

Pivotal Statistics for Testing Structural Parameters in Instrumental Variables Regression

Related objects