dvmisc (version 1.1.4)

mle_gamma_lnorm: Maximum Likelihood Estimation for X[1], ..., X[n] ~ Gamma(alpha, beta) Lognormal(mu, sigsq)

Description

Each observation is assumed to be the product of a Gamma(alpha, beta) and Lognormal(mu, sigsq) random variable. Performs maximization via nlminb. alpha and beta correspond to the shape and scale (not shape and rate) parameters described in GammaDist, and mu and sigsq correspond to meanlog and sdlog^2 in Lognormal.

Usage

mle_gamma_lnorm(x, gamma_mean1 = FALSE, lnorm_mean1 = TRUE,
  integrate_tol = 1e-08, estimate_var = FALSE, ...)

Arguments

x

Numeric vector.

gamma_mean1

Whether to use restriction that the Gamma variable is mean-1.

lnorm_mean1

Whether to use restriction that the lognormal variable is mean-1.

integrate_tol

Numeric value specifying the tol input to hcubature.

estimate_var

Logical value for whether to return Hessian-based variance-covariance matrix.

...

Additional arguments to pass to nlminb.

Value

List containing:

1. Numeric vector of parameter estimates.

2. Variance-covariance matrix (if estimate_var = TRUE).

3. Returned nlminb object from maximizing the log-likelihood function.

4. Akaike information criterion (AIC).

Examples

# NOT RUN {
# Generate 1,000 values from Gamma(0.5, 1) x Lognormal(-1.5/2, 1.5) and 
# estimate parameters
# }
# NOT RUN {
set.seed(123)
x <- rgamma(1000, 0.5, 1) * rlnorm(1000, -1.5/2, sqrt(1.5))
mle_gamma_lnorm(x, control = list(trace = 1))
# }
# NOT RUN {

# }