Aggregate Missingness Pattern Audit
Reconcile overlapping missing counts, complete records and pairwise available counts from aggregate patterns.
Your entries stay in this page’s memory and are not submitted to us. Downloads are generated locally. Reloading or leaving the page clears your entries. Do not enter patient information.
Use fictional or aggregate values only. All defaults are hypothetical; calculation stays in your browser.
Calculation results
Total: 100; complete across all entered variables: 70; any missing: 30.
Missing counts in variable order: 25, 20, 0
Pairwise available counts
Variable 1: 75, 70, 75
Variable 2: 70, 80, 80
Variable 3: 75, 80, 100
Rows and columns follow variable order; diagonal = observed for that variable.
Assumptions and limits
Each row is a mutually exclusive aggregate missingness pattern; each observation contributes to exactly one pattern. Columns retain the same variable order. Enter 1–8 variables, 1–256 unique patterns, and positive integer counts with total at most 100 million. Combine duplicate patterns first; omit zero-frequency rows. Missing-by-variable counts can overlap and must not be summed to obtain any-missing count. Pairwise counts show observations with both variables observed; diagonal counts show each variable observed. This descriptive audit cannot identify MCAR/MAR/MNAR, justify complete-case analysis, or recover missing values. Use synthetic or aggregate counts only.
mice: missingness patterns (its 1/0 convention is opposite) · Read the practical guide · Download blank worksheet (TXT)