TITLE(survreg @@ Regression for a parametric survival model )
USAGE(
survreg(formula, data=sys.parent(), subset, na.action,
link=c("log", "identity"),
dist=c("extreme", "logistic", "gaussian", "exponential"),
fixed, eps=0.0001, init, iter.max=10, model=F, x=F, y=F, ...)
)
ARGUMENTS(
ARG(formula@@)
a formula expression as for other regression models.
See the documentation for LANG(lm) and LANG(formula) for details.
ARG(data@@)
optional data frame in which to interpret the variables occuring in the
formula.
ARG(subset@@)
subset of the observations to be used in the fit.
ARG(na.action@@)
function to be used to handle any NAs in the data.
ARG(link@@)
transformation to be used on the y variable.
ARG(dist@@)
assumed distribution for the transformed y variable.
ARG(fixed@@)
a list of fixed parameters, most often just the scale.
(When I implement the t-dist, it will include the degrees of freedom).
ARG(eps@@)
convergence criteria for the computation.  Iteration continues until the
relative change in log likelihood is less than eps.
ARG(init@@)
optional vector of initial values for the paramters.
ARG(iter.max@@)
maximum number of iterations to be performed.
ARG(model@@)
if TRUE, the model frame is returned.
ARG(x@@)
if TRUE, then the X matrix is returned.
ARG(y@@)
if TRUE, then the y vector (or survival times) is returned.
ARG(...@@)
all the optional arguments to lm, including LANG(singular.ok).
)
PARA BOLD(VALUE)
an object of class LANG(survreg) is returned, which inherits from class LANG(glm).
PARA BOLD(Computation)
  This routine is not as robust against nearly singular X matrices as lm();
the problem occurs when we explicitly invert the covariance matrix with
solve().  This can sometimes be solved by subtracting the mean from all
continuous covariates.
BLANK

PARA BOLD( )
BLANK

EXAMPLES(
survreg(Surv(futime, fustat) ~ ecog.ps + rx, fleming, dist='extreme',
        link='log', fixed=list(scale=1))   #Fit an exponential
)
PARA ITALIC(File automatically converted from S(-PLUS) help format)
