Marona and Yohai Artificial Data
Simple artificial data set generated according the example by Marona and Yohai (1998). The data set consists of 20 bivariate normal observations generated with zero means, unit variances and correlation 0.8. The sample correlation is 0.81. Two outliers are introduced (i.e. these are 10% of the data) in the following way: two points are modified by interchanging the largest (observation 19) and smallest (observation 9) value of the first coordinate. The sample correlation becomes 0.05. This example provides a good example of the fact that a multivariate outlier need not be an outlier in any of its coordinate variables.
data(maryo)
A data frame with 20 observations on 2 variables. To introduce the outliers x[9,1] with x[19,1] are interchanged.
R. A. Marona and V. J. Yohai (1998) Robust estimation of multivariate location and scatter. In Encyclopedia of Statistical Sciences, Updated Volume 2 (Eds. S.Kotz, C.Read and D.Banks). Wiley, New York p. 590
data(maryo) getCorr(CovClassic(maryo)) ## the sample correlation is 0.81 ## Modify 10%% of the data in the following way: ## modify two points (out of 20) by interchanging the ## largest and smallest value of the first coordinate imin <- which(maryo[,1]==min(maryo[,1])) # imin = 9 imax <- which(maryo[,1]==max(maryo[,1])) # imax = 19 maryo1 <- maryo maryo1[imin,1] <- maryo[imax,1] maryo1[imax,1] <- maryo[imin,1] ## The sample correlation becomes 0.05 plot(maryo1) getCorr(CovClassic(maryo1)) ## the sample correlation becomes 0.05 getCorr(CovMcd(maryo1)) ## the (reweighted) MCD correlation is 0.79
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.