Estimation of a linear model under microaggregation by individual ranking

Microaggregation by individual ranking is one of the most commonly applied disclosure control techniques for continuous microdata. The paper studies the effect of microaggregation by individual ranking on the least squares estimation of a multiple linear regression model in continuous variables. It is shown that the naive parameter estimates are asymptotically unbiased. Moreover, the naive least squares estimates asymptotically have the same variances as the least squares estimates based on the original (non-aggregated) data. Thus, asymptotically, microaggregation by individual ranking does not induce any efficiency loss on the least squares estimation of a multiple linear regression model. Keywords: Asymptotic variance ; consistent estimation ; disclosure control ; individual ranking ; linear model ; microaggregation

MoreLess

Year of publication:	2005
Authors:	Schmid, Matthias
Publisher:	München : Techn. Univ.; Sonderforschungsbereich 386, Statistische Analyse Diskreter Strukturen
Subject:	Schätztheorie \| Multiple Regression \| Ranking-Verfahren \| Theorie

Full text |

More access options

Check Google Scholar

In German libraries (KVK)

I need help

More details

Series:	Discussion paper // Sonderforschungsbereich 386 der Ludwig-Maximilians-Universität München ; 453
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	501294732 [GVK] hdl:10419/31072 [Handle]
Source:	EconStor