MNlogitf: 'MNlogitf' or 'MNdogitf' returns log-likelihood(LL)...

In nmm: Nonlinear Multivariate Models

Description

MNlogitf or MNdogitf returns log-likelihood(LL) expression for discrete equations of "logit" or "dogit" model.

Usage

MNlogitf(ffor, transform = FALSE, separatenmm = FALSE, weight_disc = FALSE)

MNdogitf(
  ffor,
  transform = FALSE,
  separatenmm = FALSE,
  weight_disc = FALSE,
  ppardogit = NULL
)

Arguments

ffor	Discrete choice equations.
transform	if TRUE, quantile transformation (normal) is applied.
separatenmm	if TRUE, equation specific LL is calculated
weight_disc	if TRUE, equations will include equation specific weights.
ppardogit	"dogit" parameters only used in MNdogitf

Value

formula	simplified LL for each equation or joint
probs	probability expression unsimplified
expr	LL string simplified
formulat	unsimplified log(P), only if transform is TRUE
probt	unsimplified P with quantile transformation qnorm(ifelse(P)), only if transform is TRUE
expreteso	unsimplified pnorm((qnorm(P)-mean)/sd), only if transform is TRUE
probte	qnorm(P)
tval	If quantile transformation is applied
sume	Denominator of logit probability

Functions

• MNlogitf: returns log-likelihood(LL) expression for discrete equations of "logit" model.

• MNdogitf: returns log-likelihood(LL) expression for discrete equations of "dogit" model.

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")
disc_par <- get_par(parl, eq_d)
ffor <- disc_par$cheqs0
res_l <- MNlogitf(ffor, separatenmm=FALSE, transform=FALSE)
res_d <- MNdogitf(ffor, separatenmm=FALSE, transform=FALSE)

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