REDI: RATS module to estimate a robust regression

Eric Blankmeyer ()
Additional contact information
Eric Blankmeyer: Texas State University

Statistical Software Components from Boston College Department of Economics

Abstract: REDI computes a robust linear regression based on Rousseeuw's REsistant DIagnostic described in P. J. Rousseeuw and A. M. Leroy, Robust Regression and Outlier Detection, Wiley, 1987, pp. 238-245. Like other "high-breakdown" estimators (including least median of squares and least trimmed squares), REDI detects and downweights outliers and leverage points which may distort the regression estimate. REDI is computed by a resampling scheme. The user chooses the number of subsamples by setting the option ITERATIONS. Its default value, 3000 subsamples, should be adequate for most applications. The user should consult the Rousseeuw-Leroy book for additional details.

Language: RATS
Keywords: regression; robust (search for similar items in EconPapers)
Date: 2000-10-09

Downloads: (external link)
http://fmwww.bc.edu/repec/bocode/r/redi.src program code (text/plain)

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

Ordering information: This software item can be ordered from
http://repec.org/docs/ssc.php

Access Statistics for this software item

More software in Statistical Software Components from Boston College Department of Economics
Address: Boston College, 140 Commonwealth Avenue, Chestnut Hill MA 02467 USA
Contact information at EDIRC.
Series data maintained by Christopher F Baum ().