Basic Data Quality Checks in R
Code Example 11
Code
17 / 19
Code Example 11
Code
Code Example 11
r
quality_summary <- enrollment_data |>
summarise(
n_records = n(),
n_sites = n_distinct(site),
duplicate_participant_ids = n() - n_distinct(participant_id),
missing_consent_dates = sum(is.na(consent_date)),
missing_age = sum(is.na(age_years)),
age_out_of_range = sum(age_years < 18 | age_years > 120, na.rm = TRUE),
discharge_before_admission = sum(discharge_date < admission_date, na.rm = TRUE)
)
quality_summary