Report Template: NHANES Equity Summary

Standalone YAML

If you copy this template into a project report outside the book, start the file with this YAML header:

---
title: "NHANES Equity Summary"
format: html
bibliography: references.bib
---

Purpose

This runnable template shows how to pair a dashboard with a short reproducible report. The dashboard supports exploration; the report fixes one question, documents the data, and cites the source.

Question

How does mean BMI vary by income group among adults age 20-80 in the prepared NHANES Health Equity classroom dataset?

Data Source

The report uses the cached CSV snapshot at examples/nhanes-equity/data/nhanes_equity_v6.csv. The source data are derived from CDC/NCHS NHANES public-use files (Centers for Disease Control and Prevention, National Center for Health Statistics 2026).

library(tidyverse)  # AI-EDIT(2026-06-23): tidyverse-default — consolidated core library() calls into library(tidyverse)
library(knitr)

candidate_paths <- c(
  "examples/nhanes-equity/data/nhanes_equity_v6.csv",
  "../../examples/nhanes-equity/data/nhanes_equity_v6.csv"
)

data_path <- candidate_paths[file.exists(candidate_paths)][1]
if (is.na(data_path)) {
  stop("Could not find examples/nhanes-equity/data/nhanes_equity_v6.csv")
}

nhanes <- read_csv(data_path, show_col_types = FALSE)

Methods

We restricted the classroom dataset to adults age 20-80 and summarized BMI by income group. The summaries are unweighted and descriptive. They should not be interpreted as causal effects or national population estimates.

analysis_df <- nhanes |>
  filter(Age >= 20, Age <= 80)

missingness <- analysis_df |>
  summarise(
    rows = n(),
    missing_bmi = sum(is.na(BMI)),
    missing_income = sum(is.na(IncomeGroup)),
    missing_age = sum(is.na(Age))
  )

kable(missingness, caption = "Missingness check for key report variables.")

Missingness check for key report variables.

rows	missing_bmi	missing_income	missing_age
57137	1009	5395	0

Results

income_summary <- analysis_df |>
  filter(!is.na(BMI), !is.na(IncomeGroup)) |>
  group_by(IncomeGroup) |>
  summarise(
    n = n(),
    mean_bmi = mean(BMI),
    sd_bmi = sd(BMI),
    .groups = "drop"
  ) |>
  mutate(
    `BMI, mean (SD)` = sprintf("%.1f (%.1f)", mean_bmi, sd_bmi)
  ) |>
  select(IncomeGroup, n, `BMI, mean (SD)`)

kable(income_summary, caption = "Descriptive BMI summary by income group.")

Descriptive BMI summary by income group.

IncomeGroup	n	BMI, mean (SD)
High Income (>3.5)	16330	28.6 (6.3)
Low Income (<1.3)	15293	29.4 (7.5)
Middle Income	19228	29.3 (7.0)

plot_df <- analysis_df |>
  filter(!is.na(BMI), !is.na(IncomeGroup)) |>
  group_by(IncomeGroup) |>
  summarise(
    n = n(),
    mean_bmi = mean(BMI),
    .groups = "drop"
  )

ggplot(plot_df, aes(x = IncomeGroup, y = mean_bmi)) +
  geom_col(fill = "#2C7FB8") +
  geom_text(aes(label = paste0("n=", n)), vjust = -0.4, size = 3.5) +
  labs(
    title = "Mean BMI by income group",
    subtitle = "Adults age 20-80; unweighted descriptive summary",
    x = "Income group",
    y = "Mean BMI"
  ) +
  expand_limits(y = 0) +
  theme_minimal(base_size = 12)

Mean BMI by income group among adults age 20-80 in the prepared NHANES Health Equity classroom dataset. Values are unweighted and descriptive.

Limitations

• The table and figure use a prepared classroom dataset rather than raw NHANES files.
• The summaries are unweighted.
• The comparison is descriptive and does not establish causality.
• Missing BMI or income group values are excluded from the grouped summary.

Plain-Language Summary

In this classroom dataset, mean BMI differs across income groups. The result is useful for practicing reproducible reporting and dashboard interpretation, but it should be described as a descriptive pattern rather than a causal finding.

AI-Use and Audit Note

Document any AI assistance used to draft code, captions, or interpretation. State exactly which output you checked against the code, data dictionary, or rendered report.

Publishing Checklist

• Report renders from source.
• Citations resolve.
• Figures and tables are generated by code.
• Private preview is used unless the data, repository, and group privacy checks support public sharing.
• Public preview contains no restricted data, private links, credentials, or sensitive row-level examples.
• Staged files were reviewed before committing: no raw row-level data, credentials, .RData workspaces, or stray generated files, and .gitignore covers the data folder and rendered outputs — see the pre-commit privacy checklist.
• Private repository access is granted to course staff when needed.
• Canvas submission includes the repository link, report path, and latest commit hash.

Grounding Audit Prompt

Select three claims from the report. For each claim, write the supporting evidence source: code chunk, table, figure, or citation. Revise any claim that cannot be traced to evidence in the report.

Centers for Disease Control and Prevention, National Center for Health Statistics. 2026. National Health and Nutrition Examination Survey. https://wwwn.cdc.gov/nchs/nhanes/.