model.try.catch {chicane} | R Documentation |
model.try.catch
Description
Internal function for fitting model within a tryCatch loop, handling numerical errors gracefully.
Usage
model.try.catch(
model.formula,
data,
distribution = "negative-binomial",
maxit = 100,
epsilon = 1e-08,
init.theta = NULL,
start = NULL,
trace = FALSE,
verbose = FALSE
)
Arguments
model.formula |
formula |
data |
model data |
distribution |
Name of distribution of the counts. Options are 'negative-binomial', 'poisson', 'truncated-poisson', and 'truncated-negative-binomial' |
maxit |
Maximum number of IWLS iterations for fitting the model (passed to |
epsilon |
Positive convergence tolerance for Poisson and negative binomial models. Passed to |
init.theta |
Initial value of theta in negative binomial model |
start |
starting values of coefficients in linear predictor |
trace |
Logical indicating if output should be produced for each of model fitting procedure. Passed to |
verbose |
Logical indicating whether to print progress reports. |
Value
List with elements
model |
model object. Set to NULL if no model could be fit. |
expected.values |
vector of expected values for each element in original data, or vector of NAs if no model could be fit |
p.values |
vector of p-values for test of significantly higher response than expected, or vector of NAs if no model could be fit |