f_create: 'f_create' creates functions for log-likelihood of different...

In nmm: Nonlinear Multivariate Models

Description

f_create creates functions for log-likelihood of different models.

Usage

f_create(
  mn,
  data,
  fixed = 0,
  cheqs0 = NULL,
  separatenmm = FALSE,
  probt = NULL,
  tformula = NULL,
  hessian = NULL,
  transform = TRUE,
  sume = NULL
)

Arguments

mn	Expression, can be a list of equations.
data	Name of the data frame with which the function will be evaluated.
fixed	Integer, which parameter is fixed to be 0.
cheqs0	If continuous are supplied, include the expressions of errors.
separatenmm	if TRUE, separate log-likelihood for each equations is produced.
probt	Expressions of un-simplified probabilities with quantile transformation(qnorm(ifelse(P))).
tformula	unsimplified log(P)
hessian	Adds lines to check the Hessian, hessian should be the name of hessian function.
transform	if TRUE, adds lines to check conditional means
sume	Expression of summed likelihoods.

Value

Function.

Examples

eq_d <- c("ASC1 * 1 + B11_dur * dur_1" , "ASC2 * 1 + B12_dur * dur_2",
"ASC3 * 1 + B13_dur * dur_3 + B20_cost * cost_3 + B53_parkman * PbAvl_3",
"ASC4 * 1 + B14_dur * dur_4 + B20_cost * cost_4 + B34_serv * servIdx_4 + B44_stop * stopUs1R1_4")
parl <- c(paste0("ASC", 1:4), paste0("B1", 1:4, "_dur"), "B20_cost", "B53_parkman", "B34_serv",
"B44_stop")
obj <- get_par(parl, eq_d)
ffor <- obj$cheqs0
res <- MNlogitf(ffor, separatenmm=FALSE, transform=FALSE)
ff <- f_create(res$formula, data="data", fixed=1)

nmm documentation built on Jan. 7, 2021, 5:10 p.m.