Errors in Variables or Bad Leverage at Some Observations ?

Simple item page
dc.contributor.authorBlankmeyer, Eric
dc.date.accessioned2011-10-10T10:21:52Z
dc.date.available2012-02-24T10:21:52Z
dc.date.issued2011-10
dc.description.abstractErrors-in-variables is a long-standing, difficult issue in linear regression; and progress depends in part on new identifying assumptions. I characterize measurement error as bad-leverage points and assume that fewer than half the sample observations are heavily contaminated, in which case a high-breakdown robust estimator may be able to isolate and downweight or discard the problematic data. In simulations of simple and multiple regression where eiv affected 25% of the data and R2 was mediocre, one high-breakdown estimator had small bias, very good coverage, and precision that improved when the sample size increased.
dc.description.departmentFinance and Economics
dc.formatText
dc.format.extent24 pages
dc.format.medium1 file (.pdf)
dc.identifier.citationBlankmeyer, E. (2011). Errors in variables or bad leverage at some observations? Texas State University-San Marcos, San Marcos, Texas.
dc.identifier.urihttps://hdl.handle.net/10877/4102
dc.language.isoen
dc.publisherTexas State University-San Marcos
dc.subjecterrors in variables
dc.subjectmeasurement error
dc.subjecthigh-breakdown estimator
dc.subjectminimum covariance determinant
dc.subjectorthogonal regression
dc.titleErrors in Variables or Bad Leverage at Some Observations ?
dc.typePaper

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
fulltext.pdf
Size:
224.88 KB
Format:
Adobe Portable Document Format
Download

Collections

McCoy College of Business