predict.species_mix: Predict a species_mix model.

In skiptoniam/ecomix: Fitting Finite Mixture Models to Ecological Data

Predict a species_mix model.

Description

Predict species archetypes from a species_mix model. You can also predict the conditional species predictions using "prediction.type='species'".

Usage

## S3 method for class 'species_mix'
predict(
  object,
  object2 = NULL,
  newdata = NULL,
  offset = NULL,
  nboot = 0,
  alpha = 0.95,
  mc.cores = 1,
  type = "response",
  prediction.type = "archetype",
  na.action = "na.pass",
  ...
)

Arguments

object	is a matrix model returned from the species_mix model.
object2	is a species mix bootstrap object.
newdata	a matrix of new observations for prediction.
offset	an offset for prediction
nboot	Number of bootstraps (or simulations if using IPPM) to run if no object2 is provided.
alpha	confidence level. default is 0.95
mc.cores	number of cores to use in prediction. default is 1.
type	Do you want to predict the 'response' or the 'link'; ala glm style predictions.
prediction.type	Do you want to produce 'archetype' or 'species' level predictions. default is 'archetype'.
na.action	The type of action to apply to NA data. Default is "na.pass" see predict.lm for more details.
\dots	Ignored

Examples

library(ecomix)
set.seed(42)
sam_form <- stats::as.formula(paste0('cbind(',paste(paste0('spp',1:20),
collapse = ','),")~x1+x2"))
sp_form <- ~ 1
beta <- matrix(c(-2.9,-3.6,-0.9,1,.9,1.9),3,2,byrow=TRUE)
dat <- data.frame(y=rep(1,100),x1=stats::runif(100,0,2.5),
x2=stats::rnorm(100,0,2.5))
dat[,-1] <- scale(dat[,-1])
simulated_data <- species_mix.simulate(archetype_formula = sam_form,species_formula = sp_form,
data = dat,beta=beta,family="bernoulli")
fm1 <- species_mix(archetype_formula = sam_form,species_formula = sp_form,
data = simulated_data, family = 'bernoulli',  nArchetypes=3)
preds_fm1 <- predict(fm1)

skiptoniam/ecomix documentation built on Sept. 14, 2023, 6:04 a.m.