Generalized Methods of Trimmed Moments

Research output: Working paperDiscussion paperOther research output

314 Downloads (Pure)

Abstract

High breakdown-point regression estimators protect against large errors and data contamination. We adapt and generalize the concept of trimming used by many of these robust estimators so that it can be employed in the context of the generalized method of moments. The proposed generalized method of trimmed moments (GMTM) offers a globally robust estimation approach (contrary to existing only locally robust estimators) applicable in econometric models identified and estimated using moment conditions. We derive the consistency and asymptotic distribution of GMTM in a general setting, propose a robust test of overidentifying conditions, and demonstrate the application of GMTM in the instrumental variable regression. We also compare the finite-sample performance of GMTM and existing estimators by means of Monte Carlo simulation.
Original languageEnglish
Place of PublicationTilburg
PublisherEconometrics
Number of pages42
Volume2009-25
Publication statusPublished - 2009

Publication series

NameCentER Discussion Paper
Volume2009-25

Keywords

  • asymptotic normality
  • generalized method of moments
  • instrumental variables regression
  • robust estimation
  • trimming

Fingerprint Dive into the research topics of 'Generalized Methods of Trimmed Moments'. Together they form a unique fingerprint.

  • Research Output

    Generalized method of trimmed moments

    Cizek, P., Apr 2016, In : Journal of Statistical Planning and Inference. 171, p. 63-78

    Research output: Contribution to journalArticleScientificpeer-review

  • 1 Citation (Scopus)

    Cite this

    Cizek, P. (2009). Generalized Methods of Trimmed Moments. (CentER Discussion Paper; Vol. 2009-25). Econometrics.