Learn R Programming
PSsurvival (version 0.2.0)

summary.marCoxph: Summary Method for marCoxph Objects

Description

Summary Method for marCoxph Objects

Usage

# S3 method for marCoxph
summary(object, conf_level = 0.95, round.digits = 4, style = "prints", ...)

Value

If style = "prints", returns invisibly. If style = "returns", returns a list with:

logHR

Named vector of log hazard ratio estimates.

logHR_CI_lower

Named vector of lower CI bounds on log scale.

logHR_CI_upper

Named vector of upper CI bounds on log scale.

SE

Named vector of standard errors on log scale (from variance_method).

HR

Named vector of hazard ratio estimates (original scale).

HR_CI_lower

Named vector of lower CI bounds on original scale.

HR_CI_upper

Named vector of upper CI bounds on original scale.

variance_method

Variance method used.

conf_level

Confidence level used.

n_per_group

Named vector of sample sizes per group in Cox model.

events_per_group

Named vector of event counts per group in Cox model.

Arguments

object

A marCoxph object.

conf_level

Confidence level for intervals. Default 0.95.

round.digits

Number of digits for rounding displayed values. Default 4. Only used if style = "prints".

style

Output style: "prints" (print formatted tables) or "returns" (return vectors). Default "prints".

...

Additional arguments (ignored).

Details

Confidence intervals are Wald-type intervals calculated as:

  • Log scale: logHR ± z_crit * SE

  • Original scale: exp(logHR ± z_crit * SE)

The SE used depends on variance_method from the original marCoxph call:

  • "robust": Uses logHR_se_robust from sandwich estimator.

  • "bootstrap-full" or "bootstrap-strata": Uses logHR_se_bootstrap.