glmnet (version 4.1)

coxnet.deviance: Compute deviance for Cox model

Description

Compute the deviance (-2 log partial likelihood) for Cox model.

Usage

coxnet.deviance(
  pred = NULL,
  y,
  x = NULL,
  offset = NULL,
  weights = NULL,
  std.weights = TRUE,
  beta = NULL
)
coxnet.deviance0(
  pred = NULL,
  y,
  x = NULL,
  offset = NULL,
  weights = NULL,
  std.weights = TRUE,
  beta = NULL
)
coxnet.deviance2(
  pred = NULL,
  y,
  x = NULL,
  offset = NULL,
  weights = NULL,
  std.weights = TRUE,
  beta = NULL
)
coxnet.deviance3(
  pred = NULL,
  y,
  x = NULL,
  offset = NULL,
  weights = NULL,
  std.weights = TRUE,
  beta = NULL
)

Arguments

pred

Fit vector or matrix (usually from glmnet at a particular lambda or a sequence of lambdas).

y

Survival response variable, must be a Surv or stratifySurv object.

x

Optional x matrix, to be supplied if pred = NULL.

offset

Optional offset vector.

weights

Observation weights (default is all equal to 1).

std.weights

If TRUE (default), observation weights are standardized to sum to 1.

beta

Optional coefficient vector/matrix, to be supplied if pred = NULL.

Value

A vector of deviances, one for each column of predictions.

Details

Computes the deviance for a single set of predictions, or for a matrix of predictions. The user can either supply the predictions directly through the pred option, or by supplying the x matrix and beta coefficients. Uses the Breslow approach to ties.

The function first checks if pred is passed: if so, it is used as the predictions. If pred is not passed but x and beta are passed, then these values are used to compute the predictions. If neither x nor beta are passed, then the predictions are all taken to be 0.

coxnet.deviance() is a wrapper: it calls coxnet.deviance0() if the response is right-censored data, and calls coxnet.deviance3() if the response is (start, stop] survival data.

coxnet.deviance2() gives the same output as coxnet.deviance0() but is written completely in R. It is not called by coxnet.deviance(), and is kept in the package for completeness.

See Also

coxgrad

Examples

# NOT RUN {
set.seed(1)
eta <- rnorm(10)
time <- runif(10, min = 1, max = 10)
d <- ifelse(rnorm(10) > 0, 1, 0)
y <- survival::Surv(time, d)
coxnet.deviance(pred = eta, y = y)

# if pred not provided, it is set to zero vector
coxnet.deviance(y = y)

# example with x and beta
x <- matrix(rnorm(10 * 3), nrow = 10)
beta <- matrix(1:3, ncol = 1)
coxnet.deviance(y = y, x = x, beta = beta)

# example with (start, stop] data
y2 <- survival::Surv(time, time + runif(10), d)
coxnet.deviance(pred = eta, y = y2)

# example with strata
y2 <- stratifySurv(y, rep(1:2, length.out = 10))
coxnet.deviance(pred = eta, y = y2)

# }