Hi Guys, thank you all for you comments. Actually, I had a typo and you'r right that it should be "subdata[-c(11,22,33) , ]"
However, this does not work well either. I think, I know the reason: In the diagnostic diagramm (that you get with plot(linreg) ), the number which are assigned to the most salient outliers refer to the number in the row.names-vector!? When I open the speadsheet with fix(subdata) and note the case number associated with the row.names-value for the respective case, I can exclude them correctly!? For instance, the diagnostics refer to 11,22, and 33, and in the spreadsheet the associated case numbers whould be, say, 100, 101, and 102. Then I have to exclude these numbers with subdata[-c(100,101,102),] in order to eliminate the three outliers (11,22,33)!. This is really weird as I do not open the spreadsheet any time I quickly want to exclude a few outliers. Seems that R remembers that the row.names-values were the former case numbers in the dataframe from which the subset was created.... Best, Holger -- View this message in context: http://www.nabble.com/Eliminate-cases-in-a-subset-of-a-dataframe-tp25437374p25443124.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
