Learn R Programming

geomorph (version 4.0.8)

phylo.integration: Quantify phylogenetic morphological integration between two or more sets of variables under Brownian motion

Description

Function quantifies the degree of phylogenetic morphological covariation between two or more sets of Procrustes shape variables using partial least squares.

Usage

phylo.integration(
  A,
  A2 = NULL,
  phy,
  partition.gp = NULL,
  iter = 999,
  seed = NULL,
  print.progress = TRUE
)

Value

Objects of class "pls" from integration.test return a list of the following:

r.pls

The estimate of morphological integration: PLS.corr. The mean of pairwise PLS correlations between partitions is used when there are more than two partitions.

r.pls.mat

The pairwise r.pls, if the number of partitions is greater than 2.

P.value

The empirically calculated P-value from the resampling procedure.

Effect.Size

The multivariate effect size associated with sigma.d.ratio.

left.pls.vectors

The singular vectors of the left (x) block (for 2 modules only).

right.pls.vectors

The singular vectors of the right (y) block (for 2 modules only).

random.r

The correlation coefficients found in each random permutation of the resampling procedure.

XScores

Values of left (x) block projected onto singular vectors (for 2 modules only).

YScores

Values of right (y) block projected onto singular vectors (for 2 modules only).

svd

The singular value decomposition of the cross-covariances (for 2 modules only).

A1

Input values for the left block (for 2 modules only).

A2

Input values for the right block (for 2 modules only).

A1.matrix

Left block (matrix) found from A1 (for 2 modules only).

A2.matrix

Right block (matrix) found from A2 (for 2 modules only).

Pcov

The phylogenetic transformation matrix, needed for certain other analyses.

permutations

The number of random permutations used in the resampling procedure.

call

The match call.

Arguments

A

A 2D array (n x [p1 x k1]) or 3D array (p1 x k1 x n) containing Procrustes shape variables for the first block

A2

An optional 2D array (n x [p2 x k2]) or 3D array (p2 x k2 x n) containing Procrustes shape variables for the second block

phy

A phylogenetic tree of class = "phylo" - see read.tree in library ape

partition.gp

A list of which landmarks (or variables) belong in which partition: (e.g. A, A, A, B, B, B, C, C, C). This is required when only 1 dataset provided.

iter

Number of iterations for significance testing

seed

An optional argument for setting the seed for random permutations of the resampling procedure. If left NULL (the default), the exact same P-values will be found for repeated runs of the analysis (with the same number of iterations). If seed = "random", a random seed will be used, and P-values will vary. One can also specify an integer for specific seed values, which might be of interest for advanced users.

print.progress

A logical value to indicate whether a progress bar should be printed to the screen. This is helpful for long-running analyses.

Author

Dean Adams

Details

The function quantifies the degree of phylogenetic morphological integration between two or more sets of Procrustes shape variables. The approach is based on a Brownian motion model of evolution. It is assumed that the landmarks have previously been aligned using Generalized Procrustes Analysis (GPA) [e.g., with gpagen].

The function estimates the degree of morphological covariation between two or sets of variables while accounting for phylogeny using partial least squares (Adams and Felice 2014), and under a Brownian motion model of evolution. If more than two partitions are defined, the average pairwise PLS correlation is utilized as the test statistic. The observed value is statistically assessed using permutation, where data for one partition are permuted relative to the other partitions. In addition, a multivariate effect size describing the strength of the effect is estimated from the empirically-generated sampling distribution (see details in Adams and Collyer 2019). Note that this permutation is performed on phylogenetically- transformed data, so that the probability of phylogenetic association of A vs. B is similar to that of B vs. A: i.e., prob(A,B|phy)~prob(B,A|phy); thus, shuffling the correct exchangeable units under the null hypothesis of no integration (Adams and Collyer 2018).

Input for the analysis can take one of two forms. First, one can input a single dataset (as a matrix or 3D array, along with a vector describing which variables correspond to which partitions (for the case of a 3D array, which landmarks belong to which partitions is specified). Alternatively, when evaluating the integration between two structures or partitions, two datasets may be provided.

The generic functions, print, summary, and plot all work with phylo.integration. The generic function, plot, produces a two-block.pls plot. This function calls plot.pls, which produces an ordination plot. An additional argument allows one to include a vector to label points. Starting with version 3.1.0, warpgrids are no longer available with plot.pls but after making a plot, the function returns values that can be used with picknplot.shape or a combination of shape.predictor and plotRefToTarget to visualize shape changes in the plot (via warpgrids).

Similarity to two.b.pls and compare.pls

Note that phylo.integration performed on two matrices or arrays returns the same results as a phylogenetic variation of two.b.pls. It might be of interest with 3+ modules to perform separate phylogenetic integration tests between all pairwise comparisons of modules. This can be done, test by test, and the levels of integration can be compared with compare.pls. Such results are different than using the average amount of integration when more than two modules are input, as found with phylo.integration.

Notes for geomorph 3.0.4 and subsequent versions

Compared to previous versions of geomorph, users might notice differences in effect sizes. Previous versions used z-scores calculated with expected values of statistics from null hypotheses (sensu Collyer et al. 2015); however Adams and Collyer (2016) showed that expected values for some statistics can vary with sample size and variable number, and recommended finding the expected value, empirically, as the mean from the set of random outcomes. Geomorph 3.0.4 and subsequent versions now center z-scores on their empirically estimated expected values and where appropriate, log-transform values to assure statistics are normally distributed. This can result in negative effect sizes, when statistics are smaller than expected compared to the average random outcome. For ANOVA-based functions, the option to choose among different statistics to measure effect size is now a function argument.

References

Adams, D.C. and R. Felice. 2014. Assessing phylogenetic morphological integration and trait covariation in morphometric data using evolutionary covariance matrices. PLOS ONE. 9(4):e94335.

Collyer, M.L., D.J. Sekora, and D.C. Adams. 2015. A method for analysis of phenotypic change for phenotypes described by high-dimensional data. Heredity. 115:357-365.

Adams, D.C. and M.L. Collyer. 2016. On the comparison of the strength of morphological integration across morphometric datasets. Evolution. 70:2623-2631.

Adams, D.C. and M.L. Collyer. 2018. Multivariate comparative methods: evaluations, comparisons, and recommendations. Systematic Biology. 67:14-31.

Adams, D.C. and M.L. Collyer. 2019. Comparing the strength of modular signal, and evaluating alternative modular hypotheses, using covariance ratio effect sizes with morphometric data. Evolution. 73:2352-2367.

See Also

integration.test, modularity.test, and two.b.pls

Examples

Run this code
if (FALSE) {
data(plethspecies) 
Y.gpa <- gpagen(plethspecies$land)    #GPA-alignment
land.gps <- c("A","A","A","A","A","B","B","B","B","B","B") 

IT <- phylo.integration(Y.gpa$coords, partition.gp = land.gps,
  phy = plethspecies$phy)
summary(IT) # Test summary
P <- plot(IT) # PLS plot

 # Block 1 
 minx <- min(P$plot_args$x)
 maxx <- max(P$plot_args$x)
 preds <- shape.predictor(P$A1, 
 x = P$plot.args$x,
 min = minx, max = maxx)
 plotRefToTarget(mshape(P$A1), preds$min)
 plotRefToTarget(mshape(P$A1), preds$max)

 # Block 2 
 miny <- min(P$plot_args$y)
 maxy <- max(P$plot_args$y)
 preds <- shape.predictor(P$A2, 
 x = P$plot.args$y,
 min = miny, max = maxy)
 plotRefToTarget(mshape(P$A2), preds$min)
 plotRefToTarget(mshape(P$A2), preds$max)
 
 ### Visualize shape variation using picknplot.shape Because picknplot  
 ### requires user decisions, the following example
 ### is not run.
 ### For detailed options, see the picknplot help file
 # picknplot.shape(P)
}

Run the code above in your browser using DataLab