Thanks for being patient with me. I guess my problem is with understand how grouping in this particular case is used:
one of the sample codes I found online (http://www.statmethods.net/advstats/discriminant.html) library(MASS) fit <- lda(G ~ x1 + x2 + x3, data=mydata, na.action="na.omit", CV=TRUE) the "mydata" file in my case is the 3dmaskdump file with 52 columns and 671 rows (all values range between 0 and 1 after they're scaled) the other file, what I assumed was the "grouping file" (or the "vowel_feature") is the file that defines features for the vowels (i.e. column 1 of the file is vowel name (a, i, u) and every other column in a distinct combination of 0's and 1's defining the vowel (so this file has 26 columns and 254 rows). Therefore, every column that follows represents a particular "feature" of that vowel.. (hope this makes sense!!) So, the reason I wanted to return G <- vowel_feature[15] in my previous post is because I need to extract a column that represents "backness" of the vowel (while other columns represent "roundedness", "nasalization" features, etc). So what (in my mind) G <- vowel_feature[15] would return is 1 column which is 254 rows long with 0's and 1's in it. i.e. 1 0 2 1 3 1 4 0 ... .. . 254 1 I am a novice with R (so I know my questions are pretty dumb!), but I really hope I clarified my confusion a bit better. I very much appreciate your help. Looking forward to your replies. Thank you again, Cobbler -- View this message in context: http://r.789695.n4.nabble.com/Linear-Discriminant-Analysis-in-R-tp2231922p2235777.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.