single_step: Take a single step in the newton raphson algorithm

In nickseedorff/pmmhLong: Pseudo-marginal Metroplis Hastings for Efficient Multivariate Longitudinal Poisson Regression

Description

Take a single step in the newton raphson algorithm

Usage

single_step(y, f_cur, inv_cov, mu)

Arguments

y	vector, count for a specific user and time
f_cur	vector, current estimate of the mode of the latent GP
inv_cov	matrix, prior for GP precision matrix
mu	vector, linear predictor without the GP

Value

vector

Examples

inv_cov <- qr.solve(matrix(c(3, 1, 1, 3), ncol = 2))
single_step(c(1, 2), c(2, 3), inv_cov, c(-5, -4))

nickseedorff/pmmhLong documentation built on Dec. 31, 2020, 12:05 a.m.