Request: Support for Welch's Oneway Test

[jmgirard]

It would be handy to be able to estimate group means from the output of a Welch Oneway Test (as you can with a Oneway ANOVA).

fit <- oneway.test(Sepal.Length ~ Species, data = iris)
modelbased::estimate_means(fit, at = "Species")
#> Error: `x` must be a statistical model.

fit2 <- aov(Sepal.Length ~ Species, data = iris)
modelbased::estimate_means(fit2, at = "Species")
#> Estimated Marginal Means
#> 
#> Species    | Mean |   SE |       95% CI
#> ---------------------------------------
#> setosa     | 5.01 | 0.07 | [4.86, 5.15]
#> versicolor | 5.94 | 0.07 | [5.79, 6.08]
#> virginica  | 6.59 | 0.07 | [6.44, 6.73]
#> 
#> Marginal means estimated at Species

^{Created on 2022-07-24 by the reprex package (v2.0.1)}