Estimate the impact on model estimates of phylogenetic logistic regression after removing clades from the analysis, while taking into account potential interactions with intraspecific variability.
intra_clade_phyglm(
formula,
data,
phy,
clade.col,
n.species = 5,
n.sim = 100,
n.intra = 2,
Vx = NULL,
distrib = "normal",
x.transf = NULL,
btol = 50,
track = TRUE,
...
)The model formula
Data frame containing species traits with row names matching tips
in phy.
A phylogeny (class 'phylo') matching data.
The column in the provided data frame which specifies the clades (a character vector with clade names).
Minimum number of species in a clade for the clade to be
included in the leave-one-out deletion analysis. Default is 5.
Number of simulations for the randomization test.
Number of datasets resimulated taking into account intraspecific variation (see: "intra_phyglm")
Name of the column containing the standard deviation or the standard error of the predictor
variable. When information is not available for one taxon, the value can be 0 or NA
A character string indicating which distribution to use to generate a random value for the response
and/or predictor variables. Default is normal distribution: "normal" (function rnorm).
Uniform distribution: "uniform" (runif)
Warning: we recommend to use normal distribution with Vx or Vy = standard deviation of the mean.
Transformation for the predictor variable (e.g. "log" or "sqrt"). Please use this
argument instead of transforming data in the formula directly (see also details below).
Bound on searching space. For details see phyloglm
Print a report tracking function progress (default = TRUE)
Further arguments to be passed to phyloglm
The function intra_clade_phyglm returns a list with the following
components:
formula: The formula
full.model.estimates: Coefficients, aic and the optimised
value of the phylogenetic parameter (e.g. lambda) for the full model
without deleted species.
sensi.estimates: A data frame with all simulation
estimates. Each row represents a deleted clade. Columns report the calculated
regression intercept (intercept), difference between simulation
intercept and full model intercept (DIFintercept), the percentage of change
in intercept compared to the full model (intercept.perc) and intercept
p-value (pval.intercept). All these parameters are also reported for the regression
slope (DIFestimate etc.). Additionally, model aic value (AIC) and
the optimised value (optpar) of the phylogenetic parameter
(e.g. kappa or lambda, depending on the phylogenetic model used)
are reported.
null.dist: A data frame with estimates for the null distributions
for all clades analysed.
data: Original full dataset.
errors: Clades and/or iterations where deletion resulted in errors.
This function sequentially removes one clade at a time, fits a phylogenetic
logistic regression model using phyloglm and stores the
results. The impact of of a specific clade on model estimates is calculated by the
comparison between the full model (with all species) and the model without
the species belonging to a clade. This operation is repeated n.intra times for
simulated values of the dataset, taking into account intraspecific variation. At each iteration, the function
generates a random value for each row in the dataset using the standard deviation or errors supplied, and
detect the influential species within that iteration.
Additionally, to account for the influence of the number of species on each clade (clade sample size), this function also estimate a null distribution expected for the number of species in a given clade. This is done by fitting models without the same number of species in the given clade. The number of simulations to be performed is set by 'n.sim'. To test if the clade influence differs from the null expectation for a clade of that size, a randomization test can be performed using 'summary(x)'.
All phylogenetic models from phyloglm can be used, i.e. BM,
OUfixedRoot, OUrandomRoot, lambda, kappa,
delta, EB and trend. See ?phyloglm for details.
clade_phyglm detects influential clades based on
difference in intercept and/or slope when removing a given clade compared
to the full model including all species.
Currently, this function can only implement simple logistic models (i.e. \(y = a + bx\)). In the future we will implement more complex models.
Output can be visualised using sensi_plot.
Paterno, G. B., Penone, C. Werner, G. D. A. sensiPhy: An r-package for sensitivity analysis in phylogenetic comparative methods. Methods in Ecology and Evolution 2018, 9(6):1461-1467
Ho, L. S. T. and Ane, C. 2014. "A linear-time algorithm for Gaussian and non-Gaussian trait evolution models". Systematic Biology 63(3):397-408.
phyloglm, intra_phyglm,
clade_phyglm, intra_clade_phylm,
sensi_plot
# NOT RUN {
set.seed(6987)
phy = rtree(100)
x = rTrait(n=1,phy=phy,parameters=list(ancestral.state=2,optimal.value=2,sigma2=1,alpha=1))
X = cbind(rep(1,100),x)
y = rbinTrait(n=1,phy=phy, beta=c(-1,0.5), alpha=.7 ,X=X)
z = rnorm(n = length(x),mean = mean(x),sd = 0.1*mean(x))
cla <- rep(c("A","B","C","D"), each = 25)
dat = data.frame(y, x, z, cla)
intra_clade <- intra_clade_phyglm(formula=y ~ x, data = dat, phy = phy,
clade.col = "cla", n.sim = 30, n.intra = 3,
x.transf = log, Vx = "z", distrib="normal")
sensi_plot(intra_clade)
sensi_plot(intra_clade, clade = "B", graphs = 2)
# }
Run the code above in your browser using DataLab