Skip to main content
Cross Validated

Return to Answer

capitalization, punctuation, italicization, numeric list formatting
Source Link
Nick Stauner
Nick Stauner
  • 12.4k
  • 5
  • 53
  • 110

Have you tried using the morphometric approaches of Strauss & Bookstein (1982)? It seems like this may give you a relatively straightforward way to compare your populations. Here's a really brief summary, but there's much more in the paper and other morphometric publications. (1) if necessary, log-transform the 50 measurements ("dimensions") (2) PCA of these dimensions (variables) (note) PC 1 will likely explain almost all of the variance in the dimension data, and it mostly reflects overall size, so... (3) regressions of each dimension and PC 1 (4) residuals of each regression may be used in the construction of discriminant model for DA based on pre-assigned groups (populations) (5) use resubstitution error rates to assess morphometric differences between populations (6) MANOVA/ANOVA on regression residual data for both additional assessment of population differences and to identify specific dimensions that differ (note) you may want to be careful even if MANOVA results indicate real differences due to the sheer number of ANOVA

  1. If necessary, log-transform the 50 measurements ("dimensions")
  2. PCA of these dimensions (variables)
  • (note) PC 1 will likely explain almost all of the variance in the dimension data, and it mostly reflects overall size, so...
  1. Regressions of each dimension and PC 1
  2. Residuals of each regression may be used in the construction of discriminant model for DA based on pre-assigned groups (populations)
  3. Use resubstitution error rates to assess morphometric differences between populations
  4. MANOVA/ANOVA on regression residual data for both additional assessment of population differences and to identify specific dimensions that differ
  • (note) you may want to be careful even if MANOVA results indicate real differences due to the sheer number of ANOVA

Strauss, R. E. and F. L. Bookstein. 1982. The truss: bodyBody form reconstructions in morphometrics. Systematic Biology 31Systematic Biology 31:113-135113–135.

Have you tried using the morphometric approaches of Strauss & Bookstein (1982)? It seems like this may give you a relatively straightforward way to compare your populations. Here's a really brief summary, but there's much more in the paper and other morphometric publications. (1) if necessary, log-transform the 50 measurements ("dimensions") (2) PCA of these dimensions (variables) (note) PC 1 will likely explain almost all of the variance in the dimension data, and it mostly reflects overall size, so... (3) regressions of each dimension and PC 1 (4) residuals of each regression may be used in the construction of discriminant model for DA based on pre-assigned groups (populations) (5) use resubstitution error rates to assess morphometric differences between populations (6) MANOVA/ANOVA on regression residual data for both additional assessment of population differences and to identify specific dimensions that differ (note) you may want to be careful even if MANOVA results indicate real differences due to the sheer number of ANOVA

Strauss, R. E. and F. L. Bookstein. 1982. The truss: body form reconstructions in morphometrics. Systematic Biology 31:113-135.

Have you tried using the morphometric approaches of Strauss & Bookstein (1982)? It seems like this may give you a relatively straightforward way to compare your populations. Here's a really brief summary, but there's much more in the paper and other morphometric publications.

  1. If necessary, log-transform the 50 measurements ("dimensions")
  2. PCA of these dimensions (variables)
  • (note) PC 1 will likely explain almost all of the variance in the dimension data, and it mostly reflects overall size, so...
  1. Regressions of each dimension and PC 1
  2. Residuals of each regression may be used in the construction of discriminant model for DA based on pre-assigned groups (populations)
  3. Use resubstitution error rates to assess morphometric differences between populations
  4. MANOVA/ANOVA on regression residual data for both additional assessment of population differences and to identify specific dimensions that differ
  • (note) you may want to be careful even if MANOVA results indicate real differences due to the sheer number of ANOVA

Strauss, R. E. and F. L. Bookstein. 1982. The truss: Body form reconstructions in morphometrics. Systematic Biology 31:113–135.

Source Link
chris
chris
  • 11
  • 1

Have you tried using the morphometric approaches of Strauss & Bookstein (1982)? It seems like this may give you a relatively straightforward way to compare your populations. Here's a really brief summary, but there's much more in the paper and other morphometric publications. (1) if necessary, log-transform the 50 measurements ("dimensions") (2) PCA of these dimensions (variables) (note) PC 1 will likely explain almost all of the variance in the dimension data, and it mostly reflects overall size, so... (3) regressions of each dimension and PC 1 (4) residuals of each regression may be used in the construction of discriminant model for DA based on pre-assigned groups (populations) (5) use resubstitution error rates to assess morphometric differences between populations (6) MANOVA/ANOVA on regression residual data for both additional assessment of population differences and to identify specific dimensions that differ (note) you may want to be careful even if MANOVA results indicate real differences due to the sheer number of ANOVA

Strauss, R. E. and F. L. Bookstein. 1982. The truss: body form reconstructions in morphometrics. Systematic Biology 31:113-135.