Re: [MORPHMET] MANOVA
Ian, This means you have more variables than specimens, which your data file confirms. A parametric manova is not possible, because the algebra cannot be completed, because the covariance matrix will be singular. Dean Dr. Dean C. Adams Director of Graduate Education, EEB Program Professor Department of Ecology, Evolution, and Organismal Biology Iowa State University www.public.iastate.edu/~dcadams/ phone: 515-294-3834 On Fri, Sep 7, 2018 at 10:14 AM Ian F wrote: > Hey everyone, > I am trying to run MANOVA on some morphometric data to determine if three > groups of specimens are statistically distinct. but i am receiving the > error code > > Error in summary.manova(Raf.manova1) : residuals have rank 27 < 60. > > > Can anyone spot what i am doing wrong? > My data is attached and my script is as follows > > > > data1<-Classifier.table.two > > names(data1) > > > Raf.manova1<- > manova(cbind(x1,y1,x2,y2,x3,y3,x4,y4,x5,y5,x6,y6,x7,y7,x8,y8,x9,y9,x10,y10,x11,y11,x12,y12,x13,y13,x14,y14,x15,y15,x16,y16,x17,y17,x18,y18,x20,y20,x21,y21,x22,y22,x23,y23,x24,y24,x25,y25,x26,y26,x27,y27,x28,y28,x29,y29,x30,y30,x31,y31)~as.factor(group),data=data1) > > summary(Raf.manova1) > > summary(Raf.manova1,test = "Pillal") > > summary(Raf.manova1, test = "wilks") > > summary(Raf.manova1, test = "Hotelling-Lawley") > > summary(Raf.manova1, test = "Roy") > > > Thank you for your time. > -Ian > > -- > MORPHMET may be accessed via its webpage at http://www.morphometrics.org > --- > 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 morphmet+unsubscr...@morphometrics.org. > -- Dr. Dean C. Adams Director of Graduate Education, EEB Program Professor Department of Ecology, Evolution, and Organismal Biology Iowa State University -- MORPHMET may be accessed via its webpage at http://www.morphometrics.org --- 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 morphmet+unsubscr...@morphometrics.org.
[MORPHMET] MANOVA
Hey everyone, I am trying to run MANOVA on some morphometric data to determine if three groups of specimens are statistically distinct. but i am receiving the error code Error in summary.manova(Raf.manova1) : residuals have rank 27 < 60. Can anyone spot what i am doing wrong? My data is attached and my script is as follows data1<-Classifier.table.two names(data1) Raf.manova1<- manova(cbind(x1,y1,x2,y2,x3,y3,x4,y4,x5,y5,x6,y6,x7,y7,x8,y8,x9,y9,x10,y10,x11,y11,x12,y12,x13,y13,x14,y14,x15,y15,x16,y16,x17,y17,x18,y18,x20,y20,x21,y21,x22,y22,x23,y23,x24,y24,x25,y25,x26,y26,x27,y27,x28,y28,x29,y29,x30,y30,x31,y31)~as.factor(group),data=data1) summary(Raf.manova1) summary(Raf.manova1,test = "Pillal") summary(Raf.manova1, test = "wilks") summary(Raf.manova1, test = "Hotelling-Lawley") summary(Raf.manova1, test = "Roy") Thank you for your time. -Ian -- MORPHMET may be accessed via its webpage at http://www.morphometrics.org --- 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 morphmet+unsubscr...@morphometrics.org. group x1 y1 x2 y2 x3 y3 x4 y4 x5 y5 x6 y6 x7 y7 x8 y8 x9 y9 x10 y10 x11 y11 x12 y12 x13 y13 x14 y14 x15 y15 x16 y16 x17 y17 x18 y18 x19 y19 x20 y20 x21 y21 x22 y22 x23 y23 x24 y24 x25 y25 x26 y26 x27 y27 x28 y28 x29 y29 x30 y30 x31 y31 Rafalt 288014372843.903226 16002835.193548 17642780 1909.709677 27102040.612903 26182149.516129 2513 2245.419355 2388.677419 23222219.774194 23542028.870968 23641854.967742 234916782337.064516 15592255.16129 1470.258065 214313962016.354839 1334.451613 18771293 1717.548387 12581551.645161 12851387.741935 1306.16129 120813371037.935484 1457.967742 958 1650.870968 950 1844.774194 943 2038.677419 936 2204.580645 947 2378 974.483871 2557.387097 996 2737.290323 10172863 1092.193548 28941250.096774 Rafalt 3178144931321676.806452 30501868.612903 2981.580645 207428642230.225806 2720.967742 2361 2549.16129 24632364.354839 25522120.548387 2582 1859.741935 25811618.935484 254814062487.129032 1244 2375.322581 1115.516129 2230998 2073.709677 922 1875.903226 864 1660.096774 871 1409.290323 914 1178.483871 979 969.6774194 1137.129032 854 1350.935484 794 1583.741935 753 1819.548387 715 2044.354839 670 2277.16129 711 2525.967742 736 2774.774194 761 2972.580645 837 3144.387097 936 31771180.193548 Rafalt 3220155332191795.870968 31592035.741935 3064 2240.612903 2938.516129 241527932569.354839 2665.774194 27142427.903226 27082220.032258 280020222730.16129 1816.290323 26361607.419355 254514162436.548387 1247.677419 230511002152.806452 996.9354839 1956919 1734.064516 854 1503.193548 846 1267.322581 908 1029.451613 1081.419355 903 1323.290323 845 1558.16129 780 1810731.9677419 2054684.0967742 2300705.7741935 2577728.6451613 2837.516129 768 3066839.3870968 3205 1000.258065 32361269.129032 Rafalt 273315072714.258065 16542668.516129 17922636 1935.225806 25682050.967742 2456.290323 21232315.548387 21662179.806452 22142031.064516 22491863.322581 2257 1715.580645 22211594.83871 215815042065.096774 1420 1965.354839 13501851.612903 12961721.870968 1286 1556.129032 13001398.387097 12571261.645161 1279.096774 11301423.83871 109115651048.419355 17211020.677419 1889.064516 10052052.806452 989 2209.548387 10142371 1022.290323 2520.032258 10572663.774194 10972726.516129 121827301358.258065 Rafalt 2669161526761799.806452 26461969.612903 2572.580645 210624892232.225806 2382.967742 2336 2254.16129 241721152487.645161 19562497.548387 1774.741935 25191591.935484 25041449.129032 2441 1348.322581 2332
Re: [MORPHMET] MANOVA and shape data
Dear all, as an addendum to my previous message on tests for multivariate normality, I've just noticed that a new R package for this (MVN by Korkmaz et al 2014 - http://journal.r-project.org/archive/2014-2/korkmaz-goksuluk-zararsiz.pdf ) is out. Best, Carmelo -- Carmelo Fruciano Marie Curie Fellow - University of Konstanz - Konstanz, Germany Honorary Fellow - University of Catania - Catania, Italy e-mail c.fruci...@unict.it http://www.fruciano.it/research/ Carmelo Fruciano c.fruci...@unict.it ha scritto: Patrick Arnold patrick.arn...@uni-jena.de ha scritto: Dear morphometrics, I have two questions about applying MANOVA on shape data: 1. MANOVA assumes the data to be normal distributed. What is the best way to test normal distribution of multivariate shape data? And what is the best (free) software for this issue (is this embedded in PAST)? Dear Patrick, I normally use other software. However, it looks like PAST has some option for this at page 100 of the manual. On the other hand, you might want (also given the small sample sizes you mention below) to use resampling-based approaches... 2. The differences between my groups are very distinct in the CVA. This is quite normal and well known (i.e. the fact that CVA shows often very clear separation of the groups). A detailed discussion of this can be found in Mitteroecker, P. and F. Bookstein (2011). Linear Discrimination, Ordination, and the Visualization of Selection Gradients in Modern Morphometrics. Evolutionary Biology 38(1): 100-114. Most importantly, Mitteroecker Bookstein suggest using between-group principal component analysis as an alternative ordination technique. This is gaining popularity over time and, in my experience, it has been useful already in multiple cases (Franchini, Fruciano et al. 2014 - Molecular Ecology; Fruciano et al. 2014 - Biological Journal of the Linnean Society). I want to test whether these differences are statistically significant, too. As my sample size only slightly exceeds the degrees of freedom, I want to apply the MANOVA onto the CVs (i.e. decrease in the number of dependent variables). Is this possible or is it redundant? Although I have seen it done, I don't think this is a very good idea, as you have already suspected. Again, maybe resampling-based approaches might be a better choice (while, as Andrea Cardini was suggesting in some previous post, also recognizing the limitations of one's analysis). I hope this helps, Carmelo -- Carmelo Fruciano Marie Curie Fellow - University of Konstanz - Konstanz, Germany Honorary Fellow - University of Catania - Catania, Italy e-mail c.fruci...@unict.it http://www.fruciano.it/research/ -- Carmelo Fruciano Marie Curie Fellow - University of Konstanz - Konstanz, Germany Honorary Fellow - University of Catania - Catania, Italy e-mail c.fruci...@unict.it http://www.fruciano.it/research/ -- MORPHMET may be accessed via its webpage at http://www.morphometrics.org To unsubscribe from this group and stop receiving emails from it, send an email to morphmet+unsubscr...@morphometrics.org.
Re: [MORPHMET] MANOVA and shape data
Patrick Arnold patrick.arn...@uni-jena.de ha scritto: Dear morphometrics, I have two questions about applying MANOVA on shape data: 1. MANOVA assumes the data to be normal distributed. What is the best way to test normal distribution of multivariate shape data? And what is the best (free) software for this issue (is this embedded in PAST)? Dear Patrick, I normally use other software. However, it looks like PAST has some option for this at page 100 of the manual. On the other hand, you might want (also given the small sample sizes you mention below) to use resampling-based approaches... 2. The differences between my groups are very distinct in the CVA. This is quite normal and well known (i.e. the fact that CVA shows often very clear separation of the groups). A detailed discussion of this can be found in Mitteroecker, P. and F. Bookstein (2011). Linear Discrimination, Ordination, and the Visualization of Selection Gradients in Modern Morphometrics. Evolutionary Biology 38(1): 100-114. Most importantly, Mitteroecker Bookstein suggest using between-group principal component analysis as an alternative ordination technique. This is gaining popularity over time and, in my experience, it has been useful already in multiple cases (Franchini, Fruciano et al. 2014 - Molecular Ecology; Fruciano et al. 2014 - Biological Journal of the Linnean Society). I want to test whether these differences are statistically significant, too. As my sample size only slightly exceeds the degrees of freedom, I want to apply the MANOVA onto the CVs (i.e. decrease in the number of dependent variables). Is this possible or is it redundant? Although I have seen it done, I don't think this is a very good idea, as you have already suspected. Again, maybe resampling-based approaches might be a better choice (while, as Andrea Cardini was suggesting in some previous post, also recognizing the limitations of one's analysis). I hope this helps, Carmelo -- Carmelo Fruciano Marie Curie Fellow - University of Konstanz - Konstanz, Germany Honorary Fellow - University of Catania - Catania, Italy e-mail c.fruci...@unict.it http://www.fruciano.it/research/ -- MORPHMET may be accessed via its webpage at http://www.morphometrics.org To unsubscribe from this group and stop receiving emails from it, send an email to morphmet+unsubscr...@morphometrics.org.
[MORPHMET] MANOVA and shape data
Dear morphometrics, I have two questions about applying MANOVA on shape data: 1. MANOVA assumes the data to be normal distributed. What is the best way to test normal distribution of multivariate shape data? And what is the best (free) software for this issue (is this embedded in PAST)? 2. The differences between my groups are very distinct in the CVA. I want to test whether these differences are statistically significant, too. As my sample size only slightly exceeds the degrees of freedom, I want to apply the MANOVA onto the CVs (i.e. decrease in the number of dependent variables). Is this possible or is it redundant? Best regards Patrick Arnold -- Patrick Arnold, M.Sc. Institut für Spezielle Zoologie und Evolutionsbiologie mit Phyletischem Museum Friedrich-Schiller-Universität Jena Germany This message was sent through https://webmail.uni-jena.de -- MORPHMET may be accessed via its webpage at http://www.morphometrics.org To unsubscribe from this group and stop receiving emails from it, send an email to morphmet+unsubscr...@morphometrics.org.
