like.resamp: Local Optimums and Covariance from the optimizer step

In HPbayes: Heligman Pollard mortality model parameter estimation using Bayesian Melding with Incremental Mixture Importance Sampling

Description

Defines some necessary arguments for the function final.resamp. Removes NAs from the opt.mu.d and opt.cov.d matrixes.

Usage

like.resamp(K, log.like.0,  opt.cov.d, opt.mu.d, d.keep, 
d = 10, theta.dim = 8)

Arguments

K	Number of iterations at the importance sampling stage
log.like.0	A vector containing the likelihoods for each row of the prior
opt.cov.d	Covariance matrixes for the local optimums
opt.mu.d	A d x 8 matrix containing the local optimums (sets of parameters from the optimizer step)
d.keep	Number of local optimums found in the optimizer step
d	A scalar defining the number of optimizer interations. Defaults to 10
theta.dim	Number of columns in the prior matrix

Value

h.mu	A d.keep x 8 matrix containing the local optimum results
h.sig	An array with theta.dim x theta.dim x (K+d.keep) dimensions containing the covariance matrix for each local optimum
log.like	A vector of likelihoods for each row of H.k

Note

Typically for use immediately before running final.resamp or within the function hp.bm.imis

References

Poole, David and Adrian Raftery. 2000. "Inference for Deterministic Simulation Models: The Bayesian Melding Approach." Journal of the American Statistical Association 95:1244–1255.

Raftery, Adrian and Le Bao. 2009. "Estimating and Projecting Trends in HIV/AIDS Gen- eralized Epidemics Using Incremental Mixture Importance Sampling." Technical Report 560, Department of Statistics, University of Washington.

See Also

final.resamp, hp.bm.imis

HPbayes documentation built on May 2, 2019, 5:53 a.m.