Skip to content

ci.limits without se doesn't work #58

@ellessenne

Description

@ellessenne

Reproducible example:

library(rsimsum)
data("tt", package = "rsimsum")
# Works:
simsum(
  data = tt,
  estvarname = "diff",
  true = -1,
  se = "se",
  ci.limits = c("conf.low", "conf.high"),
  methodvar = "method",
  by = "dgm"
) |>
  summary(stats = "cover")
#> 'ref' method was not specified, 1 set as the reference
#> Values are:
#>  Point Estimate (Monte Carlo Standard Error)
#> 
#> Coverage of nominal 95% confidence interval:
#>  dgm               1               2
#>    1 0.9400 (0.0106) 0.9400 (0.0106)
#>    2 0.8780 (0.0146) 0.9420 (0.0105)
#>    3 0.9380 (0.0108) 0.9500 (0.0097)
#>    4 0.9020 (0.0133) 0.9420 (0.0105)
# Doesn't:
simsum(
  data = tt,
  estvarname = "diff",
  true = -1,
  ci.limits = c("conf.low", "conf.high"),
  methodvar = "method",
  by = "dgm"
) |>
  summary(stats = "cover")
#> 'ref' method was not specified, 1 set as the reference
#> Values are:
#>  Point Estimate (Monte Carlo Standard Error)

Created on 2025-02-11 with reprex v2.1.1

Likely just some control flow that omits coverage if se = NULL even though ci.limits is not?

Metadata

Metadata

Assignees

Labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions