I saw some say they use lsd for comparison, presenting some lsd values. The lsd I know well is a post hoc test of anova. Can someone please clarify this?
(Fisher's) LSD is basically method that combines the omnibius F-test for overall model significance, followed (if the previous F-test is significant) by a series of two sample t-tests to find pairwise difference. The LSD (least significant difference) is a yardstick that gives the smallest difference for which the two sample t-test will be significant.