loss_fun {BKP} | R Documentation |
Loss Function for Fitting the BKP Model
Description
Computes the loss used to fit the BKP model. Supports the Brier score (mean squared error) and negative log-loss (cross-entropy), under different prior specifications.
Usage
loss_fun(
gamma,
Xnorm,
y,
m,
prior = c("noninformative", "fixed", "adaptive"),
r0 = 2,
p0 = 0.5,
loss = c("brier", "log_loss"),
kernel = c("gaussian", "matern52", "matern32")
)
Arguments
gamma |
A numeric vector of log-transformed kernel hyperparameters. |
Xnorm |
A numeric matrix of normalized inputs (each column scaled to
|
y |
A numeric vector of observed successes (length |
m |
A numeric vector of total binomial trials (length |
prior |
Type of prior to use. One of |
r0 |
Global prior precision (only used when |
p0 |
Global prior mean (only used when |
loss |
Loss function for kernel hyperparameter tuning. One of
|
kernel |
Kernel function for local weighting. Choose from
|
Value
A single numeric value representing the total loss (to be minimized).
See Also
loss_fun_dkp
, fit.BKP
, get_prior
,
kernel_matrix
Examples
set.seed(123)
n = 10
Xnorm = matrix(runif(2 * n), ncol = 2)
m = rep(10, n)
y = rbinom(n, size = m, prob = runif(n))
loss_fun(gamma = rep(0, 2), Xnorm = Xnorm, y = y, m = m)