Hello all, I hope this isn't a silly question, but I'm only slowly learning GM analyses. I've been working with 2D data in MorphoJ, and I've gotten to the point where all the recommendations are to pull the PC or Procrustes coordinate data out and analyze them in another stats program like SPSS.
My question is, 1) what numbers, and 2) what analyses? I see people recommending doing a MANOVA in SPSS, but I don't understand on what numbers, or what that would tell me. My project is 2D outline analysis with 7 landmarks and 6 equidistant semi-landmarks between each pair (43 total). I have various categories (location, ware, time, etc.) that I want to compare similarities/variation of shape within and between groups, and try to determine if different shapes are notably linked to different areas or time periods. Differences between communities, changes over time, concepts like that. I've run PCA in MorphoJ and DFAs. I did a regression based on centroid size that indicated that 18% of shape difference could be indicated by size. (I also did a Partial Least Squares "Within a Configuration" of landmarks on different parts of the vessel, but I'm also not sure I understand what that's telling me.) I've come to the end of what I understand MorphoJ can do for me, however. Would anybody be willing to explain what statistical analyses in SPSS make sense? Thank you, - Kate Barvick -- You received this message because you are subscribed to the Google Groups "Morphmet" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/morphmet2/5cdb2c13-15de-4268-95fb-11fbcb710df2n%40googlegroups.com.
