m2LL: two times the negative log-likelihood

In jayverhoef/SpAReco: Paper on Spatial Autoregressive Models for Ecological Inference

Description

two times the negative log-likelihood

Usage

m2LL(theta, X, y, indComp, Nmat = NULL, distMat = NULL, crsStk = NULL,
  indSamp, model = NULL, rowStand = NULL, rhoBound = c(-1, 1))

Arguments

theta	covariance parameters, with overall variance parameter profiled out.
X	design matrix for fixed effects
y	vector of data for response variable
indComp	an additive independent component to the model. Default is TRUE.
Nmat	neighborhood matrix
distMat	distance matrix
crsStk	indicator matrix of whether locations cross stock boundaries
indSamp	indicator vector for wheter location was sampled. Zero, or FALSE, indicates missing value
model	either 'CAR' or 'SAR' to be the model associated with the Nmat argument
logical	value on whether Nmat should be row-standardized
rhobound	upper bound for rho. This should be determined from the eigenvalues of Nmat prior to running function

Value

two times the negative log-likelihood

Author(s)

Jay Ver Hoef jverhoef

jayverhoef/SpAReco documentation built on May 18, 2019, 5:58 p.m.