The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

tidystats

Author: Willem Sleegers License: MIT

tidystats is an R package for sharing and reporting statistics. tidystats extracts statistics from the output of statistical functions (e.g., t.test(), lm()) and stores them in a structured format. The resulting file can be shared with others and used in popular text editors to reproducibly report the statistics.

Please see below for instructions on how to install and use this package.

Do note that the package is currently in development. This means the package may contain bugs and is subject to significant changes. If you find any bugs or if you have any feedback, please let me know by creating an issue here on Github.

Installation

tidystats can be installed from CRAN.

install.packages("tidystats")

You can also install the development version from GitHub using the remotes package.

remotes::install_github("willemsleegers/tidystats")

Usage

The main function is add_stats(). The function has 2 necessary arguments:

You also need an identifier to uniquely identify the output of a statistics function. You can provide an identifier (e.g., ‘weight_height_correlation’) with the identifier argument. If you do not provide an identifer, one is automatically created for you.

Optionally, you can also specify some additional meta-information:

Once all statistics are added to the list, you can write the contents to a file using the write_stats() function.

Example

The following example shows how to combine and save the statistics from three different statistical tests.

# Conduct a t-test, regression, and an ANOVA
sleep_wide <- reshape(
  sleep,
  direction = "wide",
  idvar = "ID",
  timevar = "group",
  sep = "_"
)
sleep_test <- t.test(sleep_wide$extra_1, sleep_wide$extra_2, paired = TRUE)

ctl <- c(4.17, 5.58, 5.18, 6.11, 4.50, 4.61, 5.17, 4.53, 5.33, 5.14)
trt <- c(4.81, 4.17, 4.41, 3.59, 5.87, 3.83, 6.03, 4.89, 4.32, 4.69)
group <- gl(2, 10, 20, labels = c("Ctl", "Trt"))
weight <- c(ctl, trt)
lm_D9 <- lm(weight ~ group)

npk_aov <- aov(yield ~ block + N * P * K, npk)

# Create an empty list to add the statistics to
statistics <- list()

# Add the statistics and specify some meta-information
statistics <- statistics |>
  add_stats(sleep_test, type = "primary") |>
  add_stats(lm_D9, preregistered = TRUE) |>
  add_stats(npk_aov, notes = "An ANOVA example")

# Save the statistics to a file
write_stats(statistics, "statistics.json")

The result is a .json file that contains all the statistics from the three statistical tests. If you want to see what this file looks like, you can inspect it here.

For a fully worked out example, see vignette("introduction-to-tidystats").

Supported statistical functions

tidystats supports functions from several statistics-related packages, including stats, lme4, BayesFactor, emmeans, and others. For a full list of supported packages and their functions, see vignette("supported-functions").

In some cases you need provide a class to the add_stats() function in order for tidystats to correctly extract the statistics. You can see a list of functions that require the class argument in the documentation of the add_stats() function (?add_stats).

If you want to use tidystats on an unsupported function, there are two things you can do:

  1. Request support for the new function by creating an issue.
  2. Manually extract the statistics and add them via add_stats() using the custom_stats() function. See the vignette("custom-statistics") for more information.

Reporting statistics

The file created with the write_stats() function can be used in several text editor add-ins to reproducibly report the statistics. For more information on these add-ins, please see the tidystats website or their GitHub pages:

More information

See the tidystats website for more information, such as a FAQ, tips and tricks, as well as how to receive (and give) support.

If you have any questions or comments, feel free to create an issue here on GitHub or see the website for ways to contact me.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.