SLGP (version 1.0.2)

predictSLGP_cdf: Predict cumulative distribution values at new locations using a SLGP model

Description

Computes the posterior cumulative distribution function (CDF) values at specified covariate values using a fitted SLGP model.

Usage

predictSLGP_cdf(
  SLGPmodel,
  newNodes,
  interpolateBasisFun = "WNN",
  nIntegral = 101,
  nDiscret = 101,
  discrete = FALSE
)

Value

A data frame with newNodes and predicted CDF values, columns named cdf_1, cdf_2, ...

Arguments

SLGPmodel

An object of class SLGP-class.

newNodes

A data frame with covariate values where the SLGP should be evaluated.

interpolateBasisFun

Character string indicating the interpolation scheme for basis functions: one of "nothing", "NN", or "WNN" (default).

nIntegral

Number of integration points along the response axis.

nDiscret

Discretization resolution for interpolation (optional).

discrete

Boolean, indicates if we work with continuous pdfs (default, FALSE) or discrete probabilities

Examples

# \donttest{
# Load Boston housing dataset
library(MASS)
data("Boston")
# Set input and output ranges manually (you can also use range(Boston$age), etc.)
range_x <- c(0, 100)
range_response <- c(0, 50)

#' #Create a SLGP model but don't fit it
modelPrior <- slgp(medv ~ age,        # Use a formula to specify response and covariates
                 data = Boston,     # Use the original Boston housing data
                 method = "none",    # No training
                 basisFunctionsUsed = "RFF",         # Random Fourier Features
                 sigmaEstimationMethod = "heuristic",  # Auto-tune sigma2 (more stable)
                 predictorsLower = range_x[1],         # Lower bound for 'age'
                 predictorsUpper = range_x[2],         # Upper bound for 'age'
                 responseRange = range_response,       # Range for 'medv'
                 opts_BasisFun = list(nFreq = 200,     # Use 200 Fourier features
                                      MatParam = 5/2), # Matern 5/2 kernel
                 seed = 1)                             # Reproducibility

#Let us make 3 draws from the prior
nrep <- 3
set.seed(8)
p <- ncol(modelPrior@coefficients)
modelPrior@coefficients <- matrix(rnorm(n=nrep*p), nrow=nrep)

# Where to predict the field of pdfs ?
dfGrid <- data.frame(expand.grid(seq(range_x[1], range_x[2], 5),
seq(range_response[1], range_response[2],, 101)))
colnames(dfGrid) <- c("age", "medv")
predPriorcdf <- predictSLGP_cdf(SLGPmodel=modelPrior,
                                newNodes = dfGrid)
# }