bbdml: Maximum Likelihood for the Beta-binomial Distribution

In corncob: Count Regression for Correlated Observations with the Beta-Binomial

Maximum Likelihood for the Beta-binomial Distribution

Description

Maximum Likelihood for the Beta-binomial Distribution

Usage

bbdml(
  formula,
  phi.formula,
  data,
  link = "logit",
  phi.link = "logit",
  method = "trust",
  control = list(maxit = 1000, reltol = 1e-14),
  numerical = FALSE,
  nstart = 1,
  inits = NULL,
  ...
)

Arguments

formula	an object of class formula: a symbolic description of the model to be fitted to the abundance
phi.formula	an object of class formula without the response: a symbolic description of the model to be fitted to the dispersion
data	a data frame or phyloseq object containing the variables in the models
link	link function for abundance covariates, defaults to "logit"
phi.link	link function for dispersion covariates, defaults to "logit"
method	optimization method, defaults to "trust", or see optimr for other options
control	optimization control parameters (see optimr)
numerical	Boolean. Defaults to FALSE. Indicator of whether to use the numeric Hessian (not recommended).
nstart	Integer. Defaults to 1. Number of starts for optimization.
inits	Optional initializations as rows of a matrix. Defaults to NULL.
...	Optional additional arguments for optimr or trust

Value

An object of class bbdml.

Examples

# phyloseq example
data(soil_phylum_small)
bbdml(formula = OTU.1 ~ DayAmdmt,
phi.formula = ~ DayAmdmt,
data = soil_phylum_small)

# data frame example
seq_depth <- rpois(20, lambda = 10000)
my_counts <- rbinom(20, size = seq_depth, prob = 0.001) * 10
my_covariate <- cbind(rep(c(0,1), each = 10))
colnames(my_covariate) <- c("X1")
example_data <- data.frame("W" = my_counts, "M" = seq_depth, my_covariate)
bbdml(formula = cbind(W, M - W) ~ X1,
phi.formula = ~ X1,
data = example_data)

corncob documentation built on Aug. 31, 2023, 9:06 a.m.