tgp
function-- the generic interface to treed Gaussian process
modelingtgp.default.params(d)dim(X)[2]params..."expsep" separable power exponential family
correlation model; alternate is "exp" isotropic power family"bflat";
alternates include "b0" hierarchical Normal prior,
"bmle" empirical Bayes Normal prior, "bcart"
Bayesian linear CART style prior from Chipman et al, "b0tau"
a independent Normal prior with inverse-gamma variance.c(0.5,0.1,1.0,1.0) starting values for range $d$,
nugget $g$, $\sigma^2$, and $\tau^2$rep(0,d) starting values for beta linear parametersc(0.25,2,10) tree prior process parameters
c(alpha, beta, nmin) specifying
$$p_{\mbox{\tiny split}}(\eta, \mathcal{T}) =
\alpha*(1+\eta)^\beta$$
with zero probability to trees
with partitions containing less than nmin data pointsc(5,10) $\sigma^2$ inverse-gamma prior
parameters c(a0, g0) where g0 is scale (1/rate) parameterc(5,10) $\tau^2$ inverse-gamma
prior parameters c(a0, g0) where g0 is scale (1/rate) parameterc(a1,g1,a2,g2) where g1 and
g2 are scale (1/rate) parametersc(a1,g1,a2,g2) where g1 and
g2 are scale (1/rate) parameters; default reduces to simple exponential priorc(10,0.2,10)
Limiting Linear model parameters c(g, t1, t2), with growth parameter g > 0
minimum parameter t1 >= 0 and maximum parameter t1 >= 0, where
t1 + t2 <= 1<="" code=""> specifies $$p(b|d)=t_1 +
\exp\left{\frac{-g(t_2-t_1)}{d-0.5}\right}$$"fixed" Hierarchical exponential distribution
parameters to a1, g1, a2, and g2
of the prior distribution for the range parameter d.p;
fixed indicates that the hierarchical prior is "fixed" Hierarchical exponential
distribution parameters to a1, g1,
a2, and g2 of the prior distribution for the nug
parameter nug.p; "fixed" indicates that the
hierarchical prior is c(0.2,10) Hierarchical exponential distribution prior for
a0 and g0 of the prior distribution for the s2
parameter s2.p; "fixed" indicates that the
hierarchical prior is c(0.2,10) Hierarchical exponential distribution prior for
a0 and g0 of the prior distribution for the s2
parameter tau2.p; "fixed" indicates that the
hierarchical prior is dQuote{turned off}Gramacy, R. B., Lee, H. K. H., & Macready, W. (2005). Adaptive Exploration of Computer Experiment Parameter Spaces. submitted to JCGS, available as UCSC Technical Report ams2005-16
Gramacy, R. B. & Lee, H. K. H. (2005). Gaussian Processes and Limiting Linear Models. available as UCSC Technical Report ams2005-17
tgp