# LaplaceMetropolis_admkr: Laplace-Metropolis estimator of log marginal likelihood In bbemkr: Bayesian bandwidth estimation for multivariate kernel regression with Gaussian error

## Description

As pointed out by Raftery (1996), the Laplace-Metropolis estimator performs well in calculating log marginal likelihood among other methods considered.

## Usage

 ```1 2``` ```LaplaceMetropolis_admkr(theta, data_x, data_y, method = c("likelihood", "L1center", "median")) ```

## Arguments

 `theta` MCMC output `data_x` Regressors `data_y` Response variable `method` Computing method. `L1center` and `median` are computationally fast

## Details

The idea of the Laplace-Metropolis estimator is to avoid the limitations of the Laplace method by using posterior simulation to estimate the quantities it needs. The Laplace method for integrals is based on a Taylor series expansion of the real-valued function f(u) of the d-dimensional vector u, and yields the approximation P(D)\approx (2*pi)^(d/2)|A|^(1/2)P(D|θ)P(θ), where θ is the posterior mode of h(θ)=log(P(D|θ)P(θ)), A is minus the inverse Hessian of h(θ) evaluated at theta, and d is the dimension of θ.

The simplest way to estimate θ from posterior simulation output, and probably the most accurate, is to compute h(θ^(t)) for each t=1,…,T and take the value for which it is largest.

## Value

Log marginal likelihood

Han Lin Shang

## References

I. Ntzoufras (2009) Bayesian Modeling Using WinBUGS. John Wiley and Sons, Inc. New Jersey.

S. M. Lewis and A. E. Raftery (1997) Estimating Bayes factors via posterior simulation with the Laplace-Metropolis estimator, Journal of the American Statistical Association, 92(438), 648-655.

A. E. Raftery (1996) Hypothesis testing and model selection, in Markov Chain Monte Carlo In Practice by W. R. Gilks, S. Richardson and D. J. Spiegelhalter, Chapman and Hall, London.

`logdensity_admkr`, `logpriors_admkr`, `loglikelihood_admkr`, `mcmcrecord_admkr`