Construct a region from already computed sufficient statistics — emax_region_from

Uses the same assumptions and calibrations as [emax_region()]. The variance must be the pooled within-dose variance with `sum(counts) - length(x)` degrees of freedom, not a standard error, model residual variance, or population variance. Counts are positive integers. Different replication counts at different doses are supported.

Usage

emax_region_from_summary(
  x,
  counts,
  means,
  pooled_variance,
  D = max(x),
  alpha = 0.05,
  calibration = c("contrast", "mean")
)

Arguments

x: Nonempty numeric vector of observed doses.
counts: Replication counts, one per ordered distinct dose.
means: Dose-specific sample means, in the same order as `x`.
pooled_variance: Positive finite pooled within-dose variance.
D: Positive upper dose endpoint. Defaults to the maximum supplied dose.
alpha: Error probability strictly between zero and one.
calibration: Either `"contrast"` (primary method) or `"mean"` (full mean-region benchmark).

Value

An `emax_region` object.