---

DESCRIPTION:

Classes of objects that result from fitting a parametric survival model.

---

GENERATION:

This class of objects is returned by the survreg function to represent a fitted parametric survival model. Class survreg inherits from class glm, since it is fit by iterative reweighted least squares; the object returned has all the components of a weighted least squares object.

---

METHODS:

Objects of this class have methods for the functions print, summary, predict, and residuals.

---

STRUCTURE:

The following components must be included in a legitimate survreg object. The residuals, fitted values, coefficients and effects should be extracted by the generic functions of the same name, rather than by the "$" operator.

coefficients:

the coefficients of the linear.predictors, which multiply the columns of the model matrix. It does not include the estimate of error (sigma). The names of the coefficients are the names of the single-degree-of-freedom effects (the columns of the model matrix). If the model is over-determined there will be missing values in the coefficients corresponding to nonestimable coefficients.

family:

a 2 element character vector giving the name of the family and the link; mainly for printing purposes.

parms:

the parameters of the model that are not coefficients of the model matrix. The first of these will always be log(sigma).

fixed:

a vector the same length as parms, where 1 indicates a parameter that was fixed at its starting value and was not part of the iteration.

var:

the final variance matrix, including both coefficients and free parameters.

dresiduals:

the deviance residuals.

deviance:

minus twice the difference between the maximized log-likelihood under the fitted model and a saturated model. Similar to the residual sum of squares.

null.deviance:

the deviance corresponding to the model with only an intercept term, and with parms fixed at their final values.

loglik:

the log-likelihood for the final model.

The object will also have the components of a glm object not mentioned above: linear predictors, fitted.values, residuals, effects, R, rank, assign, df.residual, weights, call, iter, contrasts, terms and formula. See glm.object.

---

SEE ALSO:

glm.object , lm.object , survreg .