warmup_gaussian: Burn-in period

In bbemkr: Bayesian bandwidth estimation for multivariate kernel regression with Gaussian error

Description

By minimizing the cost value, the function estimates the bandwidths of the regressors and normal error variance parameter for the burn-in period

Usage

warmup_gaussian(x, inicost, mutsizp, warm = 100, prob = 0.234, data_x, data_y,
       prior_p = 2, prior_st = 1)

Arguments

x	Log of square bandwidths
inicost	Cost value
mutsizp	Step size of random-walk Metropolis algorithm
warm	Number of burn-in iterations
prob	Optimal covergence rate of random-walk Metropolis algorithm
data_x	Regressors
data_y	Response variable
prior_p	Hyperparameter of the inverse-gamma prior
prior_st	Hyperparameter of the inverse-gamma prior

Value

x	Log of square bandwidths
sigma2	Estimate of normal error variance
cost	Cost value
mutsizplast	Final step size of random-walk Metropolis algorithm
mutsizp	Step size of random-walk Metropolis algorithm

Author(s)

Han Lin Shang

See Also

mcmcrecord_gaussian, logdensity_gaussian, loglikelihood_gaussian, logpriors_gaussian

bbemkr documentation built on May 1, 2019, 10:53 p.m.