misclassification in binary variables

Christopher Bollinger

from Palgrave Macmillan

Abstract: Misclassification of binary variables is the first case of non-classical measurement error considered. Similar to the classical errors-in-variables result, misclassification of a binary regressor leads to attenuation of slope coefficient estimates in linear regression. Classical instrumental variables will not address the problem. Bounds results under a number of different sets of assumptions can be derived. When the dependent variable is binary, misclassification also leads to slope attenuation. Some identification results are available in this case.

Keywords: binary variables; dependent variable; measurement error; misclassification; regression (search for similar items in EconPapers)
JEL-codes: C13 C25 (search for similar items in EconPapers)
Date: 2010
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.dictionaryofeconomics.com/article?id=pde2010_M000617 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:pal:dofeco:v:4:year:2010:doi:3832

Ordering information: This item can be ordered from
http://www.dictionar ... lp/faq#_Toc198623697

Access Statistics for this chapter

More chapters in The New Palgrave Dictionary of Economics from Palgrave Macmillan
Bibliographic data for series maintained by Sheeja Sanoj ( this e-mail address is bad, please contact ).