Basic Data Quality Checks in R

r

site_quality_summary <- enrollment_data |>
  group_by(site) |>
  summarise(
    n_records = n(),
    missing_consent_dates = sum(is.na(consent_date)),
    missing_age = sum(is.na(age_years)),
    duplicate_ids = n() - n_distinct(participant_id),
    .groups = "drop"
  ) |>
  arrange(desc(missing_consent_dates))

site_quality_summary