The objective of this package is to perform statistical inference using an expressive statistical grammar that coheres with the
tidyverse design framework.
To install the current stable version of
infer from CRAN:
To install the developmental version of
infer, make sure to install
remotes first. The
pkgdown website for this developmental version is at https://infer.netlify.com.
To install the cutting edge version of
infer (do so at your own risk), make sure to install
remotes first. This version was last updated on 2018-07-11 12:19:33.
install.packages("remotes") remotes::install_github("tidymodels/infer", ref = "develop")
To see the things we are working on with the package as vignettes/Articles, check out the developmental
pkgdown site at https://infer-dev.netlify.com.
We welcome others helping us make this package as user friendly and efficient as possible. Please review our contributing and conduct guidelines. Of particular interest is helping us to write
testthat tests and help us in building vignettes that show how to (and how NOT to) use the package. By participating in this project you agree to abide by its terms.
These examples assume that
mtcars has been overwritten so that the variables
mtcars <- as.data.frame(mtcars) %>% mutate(cyl = factor(cyl), vs = factor(vs), am = factor(am), gear = factor(gear), carb = factor(carb))
Hypothesis test for a difference in proportions (using the formula interface
y ~ x in
mtcars %>% specify(am ~ vs, success = "1") %>% hypothesize(null = "independence") %>% generate(reps = 100, type = "permute") %>% calculate(stat = "diff in props", order = c("1", "0"))
Confidence interval for a difference in means (using the non-formula interface giving both the
explanatory variables in
mtcars %>% specify(response = mpg, explanatory = am) %>% generate(reps = 100, type = "bootstrap") %>% calculate(stat = "diff in means", order = c("1", "0"))
Note that the formula and non-formula interfaces work for all implemented inference procedures in
infer. Use whatever is more natural for you. If you will be doing modeling using functions like
glm(), we recommend you begin to use the formula
y ~ x notation as soon as possible though.
Other examples are available in the package vignettes.