survreg_tidiers {broom} | R Documentation |
Tidies the coefficients of a parametric survival regression model, from the "survreg" function, adds fitted values and residuals, or summarizes the model statistics.
## S3 method for class 'survreg' tidy(x, conf.level = 0.95, ...) ## S3 method for class 'survreg' augment(x, data = stats::model.frame(x), newdata, type.predict = "response", type.residuals = "response", ...) ## S3 method for class 'survreg' glance(x, conf.level = 0.95, ...)
x |
a "survreg" model |
conf.level |
confidence level for CI |
... |
extra arguments (not used) |
data |
original data; if it is not provided, it is reconstructed
as best as possible with |
newdata |
New data to use for prediction; optional |
type.predict |
type of prediction, default "response" |
type.residuals |
type of residuals to calculate, default "response" |
When the modeling was performed with na.action = "na.omit"
(as is the typical default), rows with NA in the initial data are omitted
entirely from the augmented data frame. When the modeling was performed
with na.action = "na.exclude"
, one should provide the original data
as a second argument, at which point the augmented data will contain those
rows (typically with NAs in place of the new columns). If the original data
is not provided to augment
and na.action = "na.exclude"
, a
warning is raised and the incomplete rows are dropped.
All tidying methods return a data.frame without rownames, whose structure depends on the method chosen.
tidy
returns a data.frame with one row for each term
term |
name of term |
estimate |
estimate of coefficient |
stderror |
standard error |
statistic |
Z statistic |
p.value |
p-value |
conf.low |
low end of confidence interval |
conf.high |
high end of confidence interval |
augment
returns the original data.frame with the following
additional columns:
.fitted |
Fitted values of model |
.se.fit |
Standard errors of fitted values |
.resid |
Residuals |
glance
returns a one-row data.frame with the columns:
iter |
number of iterations |
df |
degrees of freedom |
statistic |
chi-squared statistic |
p.value |
p-value from chi-squared test |
logLik |
log likelihood |
AIC |
Akaike information criterion |
BIC |
Bayesian information criterion |
df.residual |
residual degrees of freedom |
if (require("survival", quietly = TRUE)) { sr <- survreg(Surv(futime, fustat) ~ ecog.ps + rx, ovarian, dist="exponential") td <- tidy(sr) augment(sr, ovarian) augment(sr) glance(td) # coefficient plot library(ggplot2) ggplot(td, aes(estimate, term)) + geom_point() + geom_errorbarh(aes(xmin = conf.low, xmax = conf.high), height = 0) + geom_vline(xintercept = 0) }