(original) (raw)

--- title: "Confidence intervals and tests in emmeans" author: "emmeans package, Version `r packageVersion('emmeans')`" output: emmeans::.emm_vignette vignette: > %\VignetteIndexEntry{Confidence intervals and tests} %\VignetteEngine{knitr::rmarkdown} %\VignetteEncoding{UTF-8} --- ```{r, echo = FALSE, results = "hide", message = FALSE} require("emmeans") knitr::opts_chunk$set(fig.width = 4.5, class.output = "ro") ```## Contents {#contents} This vignette describes various ways of summarizing `emmGrid` objects. 1. [`summary()`, `confint()`, and `test()`](#summary) 2. [Back-transforming to response scale](#tran) (See also the ["transformations" vignette](transformations.html)) 3. [Multiplicity adjustments](#adjust) 4. [Using "by" variables](#byvars) 5. [Joint (omnibus) tests](#joint) 6. [Testing equivalence, noninferiority, nonsuperiority](#equiv) 7. Graphics (in ["basics" vignette](basics.html#plots)) [Index of all vignette topics](vignette-topics.html) ## `summary()`, `confint()`, and `test()` {#summary}The most important method for `emmGrid` objects is `summary()`. For one thing, it is called by default when you display an `emmeans()` result. The `summary()` function has a lot of options, and the detailed documentation via `help("summary.emmGrid")` is worth a look. For ongoing illustrations, let's re-create some of the objects in the ["basics" vignette](basics.html) for the `pigs` example: ```{r} mod4 <- lm(inverse(conc) ~ source + factor(percent), data = pigs) RG <- ref_grid(mod4) EMM.source <- emmeans(RG, "source") ``` Just `summary(