Back to Skills

generate-statistical-tables

pjt222
Updated 2 days ago
4 views
17
2
17
View on GitHub
Metaworddesign

About

This skill generates publication-ready statistical tables in R using packages like gt, kableExtra, or flextable. It creates descriptive statistics, regression results, ANOVA tables, and APA-formatted outputs for academic papers. Use it when formatting analysis results for Quarto, R Markdown, or manuscript reports.

Quick Install

Claude Code

Recommended
Primary
npx skills add pjt222/agent-almanac -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/pjt222/agent-almanac
Git CloneAlternative
git clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/generate-statistical-tables

Copy and paste this command in Claude Code to install this skill

Documentation

Generate Statistical Tables

Pub-ready stat tables for reports + manuscripts.

Use When

  • Descriptive stats tables
  • Regression / ANOVA output format
  • Correlation matrices
  • APA-style academic
  • Quarto / R Markdown tables

In

  • Required: stat results (models, summaries)
  • Required: out format (HTML, PDF, Word)
  • Optional: style guide (APA, journal)
  • Optional: numbering scheme

Do

Step 1: Choose pkg

PackageBest forFormats
gtHTML, general-purposeHTML, PDF, Word
kableExtraLaTeX/PDF documentsPDF, HTML
flextableWord documentsWord, PDF, HTML
gtsummaryClinical/statistical summariesAll via gt/flextable

→ Pkg selected by format + use case, installed + loadable.

If err: missing → install.packages("gt") (or proper). gtsummary needs gt + gtsummary.

Step 2: Descriptive stats

library(gt)

descriptives <- data |>
  group_by(group) |>
  summarise(
    n = n(),
    M = mean(score, na.rm = TRUE),
    SD = sd(score, na.rm = TRUE),
    Min = min(score, na.rm = TRUE),
    Max = max(score, na.rm = TRUE)
  )

gt(descriptives) |>
  tab_header(
    title = "Table 1",
    subtitle = "Descriptive Statistics by Group"
  ) |>
  fmt_number(columns = c(M, SD), decimals = 2) |>
  fmt_number(columns = c(Min, Max), decimals = 1) |>
  cols_label(
    group = "Group",
    n = md("*n*"),
    M = md("*M*"),
    SD = md("*SD*")
  )

gt object w/ M, SD, n grouped, italic headers.

If err: group_by() unexpected → verify var + levels. fmt_number() err → numeric cols.

Step 3: Regression results

model <- lm(outcome ~ predictor1 + predictor2 + predictor3, data = data)

library(gtsummary)

tbl_regression(model) |>
  bold_p() |>
  add_glance_source_note(
    include = c(r.squared, adj.r.squared, nobs)
  ) |>
  modify_header(label = "**Predictor**") |>
  modify_caption("Table 2: Regression Results")

→ Regression table w/ bold p, fit stats note, caption.

If err: tbl_regression() fail → verify model obj (lm, glm). add_glance_source_note() err → check broom::glance(model).

Step 4: Correlation matrix

library(gt)

cor_matrix <- cor(data[, c("var1", "var2", "var3", "var4")],
                  use = "pairwise.complete.obs")

# Format lower triangle
cor_matrix[upper.tri(cor_matrix)] <- NA

as.data.frame(cor_matrix) |>
  tibble::rownames_to_column("Variable") |>
  gt() |>
  fmt_number(decimals = 2) |>
  sub_missing(missing_text = "") |>
  tab_header(title = "Table 3", subtitle = "Correlation Matrix")

→ Lower-triangle cor matrix w/ blanked upper, 2 dec, caption.

If err: sub_missing() not blanking → check NA set. Non-numeric → cor() fails → filter numeric.

Step 5: ANOVA table

aov_result <- aov(score ~ group * condition, data = data)

library(gtsummary)

tbl_anova <- broom::tidy(aov_result) |>
  gt() |>
  fmt_number(columns = c(sumsq, meansq, statistic), decimals = 2) |>
  fmt_number(columns = p.value, decimals = 3) |>
  cols_label(
    term = "Source",
    df = md("*df*"),
    sumsq = md("*SS*"),
    meansq = md("*MS*"),
    statistic = md("*F*"),
    p.value = md("*p*")
  ) |>
  tab_header(title = "Table 4", subtitle = "ANOVA Results")

→ ANOVA w/ Source, df, SS, MS, F, p. Interactions labeled, p to 3 dec.

If err: broom::tidy(aov_result) unexpected cols → verify aov obj. Type III SS → car::Anova(model, type = 3).

Step 6: Save

# Save as HTML
gtsave(my_table, "table1.html")

# Save as Word
gtsave(my_table, "table1.docx")

# Save as PNG image
gtsave(my_table, "table1.png")

# For LaTeX/PDF (kableExtra)
kableExtra::save_kable(kable_table, "table1.pdf")

→ Saved to format. Opens correctly.

If err: gtsave() Word fail → install webshot2. PDF via kableExtra → install TinyTeX/MiKTeX.

Step 7: Embed in Quarto

```{r}
#| label: tbl-descriptives
#| tbl-cap: "Descriptive Statistics by Group"

gt(descriptives) |>
  fmt_number(columns = c(M, SD), decimals = 2)
```

See @tbl-descriptives for summary statistics.

→ Renders inline w/ @tbl-* cross-ref + caption. Adapts to format.

If err: no render → chunk label tbl- prefix. PDF formatting lost → switch gt → kableExtra.

Check

  • Renders in target format
  • Consistent number format
  • Stat notation per style (italic, symbols)
  • Clear caption + numbering
  • Meaningful headers
  • Notes/footnotes explain abbrevs + sig markers

Traps

  • gt in PDF: limited. Use kableExtra for LaTeX.
  • Rounding inconsistency: fmt_number() (gt) / format() not round().
  • Missing values: sub_missing() (gt) or options(knitr.kable.NA = "").
  • Wide PDF: landscape() or font reduction.
  • APA number: no leading zero when ≤1 (p, corr): ".03" not "0.03".

  • format-apa-report — APA manuscript tables
  • create-quarto-report — embed in reports
  • build-parameterized-report — param-adaptive tables

GitHub Repository

pjt222/agent-almanac
Path: i18n/caveman-ultra/skills/generate-statistical-tables
0
agentsagentskillsai-assisted-developmentclaude-codeskillsteams

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

polymarket

Meta

This skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.

View skill

creating-opencode-plugins

Meta

This skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.

View skill

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill