Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/jacob-long/jtools

Tools for summarizing/visualizing regressions and other helpful stuff
https://github.com/jacob-long/jtools

r r-package social-sciences

Last synced: 3 months ago
JSON representation

Tools for summarizing/visualizing regressions and other helpful stuff

Awesome Lists containing this project

README 

        
---

output: github_document

---



```{r, echo = FALSE}

knitr::opts_chunk$set(

  collapse = FALSE,

  comment = "#>",

  fig.path = "man/figures/",

  fig.width = 6.5,

  fig.height = 4,

  render = knitr::normal_print,

  # dev.args=list(type="cairo"),

  # dev = "CairoPNG",

  dpi = 175,

  retina = 1

)

library(jtools)

```



# jtools 



[![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/jtools)](https://cran.r-project.org/package=jtools) 

[![Total Downloads](https://cranlogs.r-pkg.org/badges/grand-total/jtools)](https://cran.r-project.org/package=jtools)

[![CII Best Practices](https://bestpractices.coreinfrastructure.org/projects/2527/badge)](https://bestpractices.coreinfrastructure.org/projects/2527)

[![R-CMD-check](https://github.com/jacob-long/jtools/workflows/R-CMD-check/badge.svg)](https://github.com/jacob-long/jtools/actions) 

[![AppVeyor Build Status](https://ci.appveyor.com/api/projects/status/github/jacob-long/JTools?branch=master&svg=true)](https://ci.appveyor.com/project/jacob-long/JTools) 

[![codecov](https://codecov.io/gh/jacob-long/jtools/branch/master/graph/badge.svg)](https://app.codecov.io/gh/jacob-long/jtools) 

[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-brightgreen.svg)](https://www.gnu.org/licenses/gpl-3.0)



This package consists of a series of functions created by the author (Jacob)

to automate otherwise tedious research tasks. At this juncture, the unifying

theme is the more efficient presentation of regression analyses. There are 

a number of functions for other programming and statistical purposes as 

well. Support for the `survey` package's `svyglm` objects as well as weighted

regressions is a common theme throughout.



**Notice:** As of `jtools` version 2.0.0, all functions dealing with 

interactions (e.g., `interact_plot()`, `sim_slopes()`, `johnson_neyman()`) have

been moved to a new package, aptly named 

[`interactions`](https://interactions.jacob-long.com).



## Installation



For the most stable version, simply install from CRAN.



```r

install.packages("jtools")

```



If you want the latest features and bug fixes then you can download from

Github. To do that you will need to have `devtools` installed if you don't 

already:



```r

install.packages("devtools")

```



Then install the package from Github.



```r

devtools::install_github("jacob-long/jtools")

```



To see what features are on the roadmap, check the issues

section of the repository, especially the "enhancement" tag. Closed issues

may be of interest, too, since they may be fixed in the Github version but not

yet submitted to CRAN.



## Usage



Here's a synopsis of the current functions in the package:



### Console regression summaries (`summ()`)



`summ()` is a replacement for `summary()` that provides the user several options

for formatting regression summaries. It supports `glm`, `svyglm`, and `merMod`

objects as input as well. It supports calculation and reporting of

robust standard errors via the `sandwich` package.



Basic use:



```{r}

data(movies)

fit <- lm(metascore ~ budget + us_gross + year, data = movies)

summ(fit)

```



It has several conveniences, like re-fitting your model with

scaled variables (`scale = TRUE`). You have the option to leave the

outcome variable in its original scale (`transform.response = TRUE`),

which is the default for scaled models. I'm a fan of Andrew Gelman's 2

SD standardization method, so you can specify by how many standard deviations 

you would like to rescale (`n.sd = 2`). 



You can also get variance inflation factors (VIFs) and partial/semipartial

(AKA part) correlations. Partial correlations are only available for OLS

models. You may also substitute confidence intervals in place of standard 

errors and you can choose whether to show p values.



```{r}

summ(fit, scale = TRUE, vifs = TRUE, part.corr = TRUE, confint = TRUE, pvals = FALSE)

```



Cluster-robust standard errors:



```{r}

data("PetersenCL", package = "sandwich")

fit2 <- lm(y ~ x, data = PetersenCL)

summ(fit2, robust = "HC3", cluster = "firm")

```



Of course, `summ()` like `summary()` is best-suited for interactive use. When

it comes to sharing results with others, you want sharper output and probably

graphics. `jtools` has some options for that, too.



### LaTeX-, Word-, and RMarkdown-friendly regression summary tables (`export_summs()`)



For tabular output, `export_summs()` is an interface to the `huxtable`

package's `huxreg()` function that preserves the niceties of `summ()`,

particularly its facilities for robust standard errors and standardization. 

It also concatenates multiple models into a single table.



```{r eval = F}

fit <- lm(metascore ~ log(budget), data = movies)

fit_b <- lm(metascore ~ log(budget) + log(us_gross), data = movies)

fit_c <- lm(metascore ~ log(budget) + log(us_gross) + runtime, data = movies)

coef_names <- c("Budget" = "log(budget)", "US Gross" = "log(us_gross)",

                "Runtime (Hours)" = "runtime", "Constant" = "(Intercept)")

export_summs(fit, fit_b, fit_c, robust = "HC3", coefs = coef_names)

```

```{r echo = FALSE, results = 'asis', warning = FALSE, eval = T}

# huxtable doesn't render right for the github_document, seems to thinks it's

# in the console

fit <- lm(metascore ~ log(budget), data = movies)

fit_b <- lm(metascore ~ log(budget) + log(us_gross), data = movies)

fit_c <- lm(metascore ~ log(budget) + log(us_gross) + runtime, data = movies)

coef_names <- c("Budget" = "log(budget)", "US Gross" = "log(us_gross)",

                "Runtime (Hours)" = "runtime", "Constant" = "(Intercept)")

e <- export_summs(fit, fit_b, fit_c, robust = "HC3", coefs = coef_names)

huxtable::print_html(e)

```



In RMarkdown documents, using `export_summs()` and the chunk option 

`results = 'asis'` will give you nice-looking tables in HTML and PDF

output. Using the `to.word = TRUE` argument will create a Microsoft Word

document with the table in it.



### Plotting regression summaries (`plot_coefs()` and `plot_summs()`)



Another way to get a quick gist of your regression analysis is to 

plot the values of the coefficients and their corresponding uncertainties

with `plot_summs()` (or the closely related `plot_coefs()`).

Like with `export_summs()`, you can still get your scaled

models and robust standard errors.



```{r}

coef_names <- coef_names[1:3] # Dropping intercept for plots

plot_summs(fit, fit_b, fit_c, robust = "HC3", coefs = coef_names)

```



And since you get a `ggplot` object in return, you can tweak and theme as

you wish.



Another way to visualize the uncertainty of your coefficients is via the

`plot.distributions` argument.



```{r}

plot_summs(fit_c, robust = "HC3", coefs = coef_names, plot.distributions = TRUE)

```



These show the 95% interval width of a normal distribution for each estimate.



`plot_coefs()` works much the same way, but without support for `summ()` 

arguments like `robust` and `scale`. This enables a wider range of 

models that have support from the `broom` package but not for `summ()`. 



### Plotting model predictions (`effect_plot()`)



Sometimes the best way to understand your model is to look at the predictions

it generates. Rather than look at coefficients, `effect_plot()` lets you plot

predictions across values of a predictor variable alongside the observed data. 



```{r}

effect_plot(fit_c, pred = runtime, interval = TRUE, plot.points = TRUE)

```



And a new feature in version `2.0.0` lets you plot *partial residuals*

instead of the raw observed data, allowing you to assess model quality after

accounting for effects of control variables.



```{r}

effect_plot(fit_c, pred = runtime, interval = TRUE, partial.residuals = TRUE)

```



Categorical predictors, polynomial terms, (G)LM(M)s, weighted data, and much

more are supported. 



### Other stuff



There are several other things that might interest you.



* `gscale()`: Scale and/or mean-center data, including `svydesign` objects

* `scale_mod()` and `center_mod()`: Re-fit models with scaled and/or

mean-centered data

* `wgttest()` and `pf_sv_test()`, which are combined in `weights_tests()`:

Test the ignorability of sample weights in regression models

* `svycor()`: Generate correlation matrices from `svydesign` objects

* `theme_apa()`: A mostly APA-compliant `ggplot2` theme

* `theme_nice()`: A nice `ggplot2` theme

* `add_gridlines()` and `drop_gridlines()`: `ggplot2` theme-changing 

convenience functions

* `make_predictions()`: an easy way to generate hypothetical predicted data

from your regression model for plotting or other purposes.



Details on the arguments can be accessed via the R documentation 

(`?functionname`). 

There are now vignettes documenting just about everything you can do as well.



## Contributing



I'm happy to receive bug reports, suggestions, questions, and (most of all) 

contributions to fix problems and add features. I prefer you use the Github

issues system over trying to reach out to me in other ways. Pull requests for 

contributions are encouraged. If you are considering writing up a bug fix

or new feature, please check out the [contributing guidelines](https://github.com/jacob-long/jtools/blob/master/CONTRIBUTING.md).



Please note that this project is released with a 

[Contributor Code of Conduct](https://github.com/jacob-long/jtools/blob/master/CONDUCT.md). By participating in this project

you agree to abide by its terms.



## License



This package is licensed under the 

[GPLv3 license](https://spdx.org/licenses/GPL-3.0-or-later.html) or any 

later version.