constraintL2: Soft L2 constraint on parameters

In dkaschek/dMod: Dynamic Modeling and Parameter Estimation in ODE Models

Soft L2 constraint on parameters

Description

Soft L2 constraint on parameters

Usage

constraintL2(mu, sigma = 1, attr.name = "prior", condition = NULL)

Arguments

mu	named numeric, the prior values
sigma	named numeric of length of mu or numeric of length one or character of length of mu or character of length one
attr.name	character. The constraint value is additionally returned in an attributed with this name
condition	character, the condition for which the constraint should apply. If NULL, applies to any condition.

Details

If sigma is numeric, the function computes the constraint value

\left(\frac{p-\mu}{\sigma}\right)^2

and its derivatives with respect to p. If sigma is a character, the function computes

\left(\frac{p-\mu}{\sigma}\right)^2 + \log(\sigma^2)

and its derivatives with respect to p and sigma. Sigma parameters being passed to the function are ALWAYS assumed to be on a log scale, i.e. internally sigma parameters are converted by exp().

Value

object of class objfn

See Also

wrss

Examples

mu <- c(A = 0, B = 0)
sigma <- c(A = 0.1, B = 1)
myfn <- constraintL2(mu, sigma)
myfn(pars = c(A = 1, B = -1))

# Introduce sigma parameter but fix them (sigma parameters
# are assumed to be passed on log scale)
mu <- c(A = 0, B = 0)
sigma <- paste("sigma", names(mu), sep = "_")
myfn <- constraintL2(mu, sigma)
pars <- c(A = .8, B = -.3, sigma_A = -1, sigma_B = 1)
myfn(pars = pars[c(1, 3)], fixed = pars[c(2, 4)])

# Assume same sigma parameter for both A and B
# sigma is assumed to be passed on log scale
mu <- c(A = 0, B = 0)
myfn <- constraintL2(mu, sigma = "sigma")
pars <- c(A = .8, B = -.3, sigma = 0)
myfn(pars = pars)

dkaschek/dMod documentation built on July 27, 2023, 11:45 p.m.