Type: Package
Title: Explain Statistical Output with Large Language Models
Version: 0.1.0
Description: Transform complex statistical output into straightforward, understandable, and context-aware natural language descriptions using Large Language Models (LLMs), making complex analyses more accessible to individuals with varying statistical expertise. It relies on the 'ellmer' package to interface with LLM providers including OpenAI https://openai.com/, Google AI Studio https://aistudio.google.com/, and Anthropic https://www.anthropic.com/ (API keys are required and managed via 'ellmer').
Depends: R (≥ 4.1.0)
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
URL: https://github.com/bgreenwell/statlingua, https://bgreenwell.github.io/statlingua/
Encoding: UTF-8
RoxygenNote: 7.3.2
Suggests: car, ellmer (≥ 0.2.0), ISLR2, knitr, lme4, lmerTest, MASS, mgcv, nlme, R6, rmarkdown, survival, tibble, tinytest
VignetteBuilder: knitr
Config/Needs/website: rmarkdown
NeedsCompilation: no
Packaged: 2025-05-29 02:08:25 UTC; bgreenwell
Author: Brandon M. Greenwell ORCID iD [aut, cre]
Maintainer: Brandon M. Greenwell <greenwell.brandon@gmail.com>
Repository: CRAN
Date/Publication: 2025-06-02 07:50:06 UTC

Explain statistical output

Description

Use an LLM to explain the output from various statistical objects using straightforward, understandable, and context-aware natural language descriptions.

Usage

explain(
  object,
  client,
  context = NULL,
  audience = c("novice", "student", "researcher", "manager", "domain_expert"),
  verbosity = c("moderate", "brief", "detailed"),
  style = c("markdown", "html", "json", "text", "latex"),
  ...
)

## Default S3 method:
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'htest'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'lm'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'glm'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'polr'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'lme'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'lmerMod'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'glmerMod'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'gam'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'survreg'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'coxph'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

## S3 method for class 'rpart'
explain(
  object,
  client,
  context = NULL,
  audience = "novice",
  verbosity = "moderate",
  style = "markdown",
  ...
)

Arguments

object

An appropriate statistical object. For example, object can be the output from calling t.test() or glm().

client

A Chat object (e.g., from calling chat_openai() or [chat_gemini()][ellmer::chat_gemini)]).

[ellmer::chat_gemini)]: R:ellmer::chat_gemini)

context

Optional character string providing additional context, such as background on the research question and information about the data.

audience

Character string indicating the target audience:

  • "novice" - Assumes the user has a limited statistics background (default).

  • "student" - Assumes the user is learning statistics.

  • "researcher" - Assumes the user has a strong statistical background and is familiar with common methodologies.

  • "manager" - Assumes the user needs high-level insights for decision-making.

  • "domain_expert" - Assumes the user is an expert in their own field but not necessarily in statistics.

verbosity

Character string indicating the desired verbosity:

  • "moderate" - Offers a balanced explanation (default).

  • "brief" - Offers a high-level summary.

  • "detailed" - Offers a comprehensive interpretation.

style

Character string indicating the desired output style:

  • "markdown" (default) - Output formatted as plain Markdown.

  • "html" - Output formatted as an HTML fragment.

  • "json" - Output structured as a JSON string parseable into an R list.

  • "text" - Output as plain text.

  • "latex" - Output as a LaTeX fragment.

...

Additional optional arguments. (Currently ignored.)

Value

An object of class "statlingua_explanation". Essentially a list with the following components:

Examples

## Not run: 
# Polynomial regression
fm1 <- lm(dist ~ poly(speed, degree = 2), data = cars)
context <- "
The data give the speed of cars (mph) and the distances taken to stop (ft).
Note that the data were recorded in the 1920s!
"
# Use Google Gemini to explain the output; requires an API key; see
# ?ellmer::chat_google_gemini for details
client <- ellmer::chat_google_gemini(echo = "none")
ex <- explain(fm1, client = client, context = context)

# Poisson regression example from ?stats::glm
counts <- c(18,17,15,20,10,20,25,13,12)
outcome <- gl(3,1,9)
treatment <- gl(3,3)
data.frame(treatment, outcome, counts) # showing data
fm2 <- glm(counts ~ outcome + treatment, family = poisson())

# Use Google Gemini to explain the output; requires an API key; see
# ?ellmer::chat_google_gemini for details
client <- ellmer::chat_google_gemini()
explain(fm2, client = client, audience = "student", verbosity = "detailed")

## End(Not run)

Print LLM explanation

Description

Print a formatted version of an LLMs explanation using cat().

Usage

## S3 method for class 'statlingua_explanation'
print(x, ...)

Arguments

x

A statlingua_explanation object.

...

Additional optional arguments to be passed to print.default().

Value

Invisibly returns the printed statlingua_explanation object.

Summarize statistical output

Description

Generate text-based summaries of statistical output that can be embedded into prompts for querying Large Language Models (LLMs). Intended primarily for internal use.

Usage

summarize(object, ...)

## Default S3 method:
summarize(object, ...)

## S3 method for class 'htest'
summarize(object, ...)

## S3 method for class 'lm'
summarize(object, ...)

## S3 method for class 'glm'
summarize(object, ...)

## S3 method for class 'polr'
summarize(object, ...)

## S3 method for class 'lme'
summarize(object, ...)

## S3 method for class 'lmerMod'
summarize(object, ...)

## S3 method for class 'glmerMod'
summarize(object, ...)

## S3 method for class 'gam'
summarize(object, ...)

## S3 method for class 'survreg'
summarize(object, ...)

## S3 method for class 'coxph'
summarize(object, ...)

## S3 method for class 'rpart'
summarize(object, ...)

Arguments

object

An object for which a summary is desired (e.g., a glm object).

...

Additional optional arguments. (Currently ignored.)

Value

A character string summarizing the statistical output.

See Also

summary().

Examples

tt <- t.test(1:10, y = c(7:20))
summarize(tt)  # prints output as a character string
cat(summarize(tt))  # more useful for reading