Calculators
Overlap Coefficient Calculator
Calculate how much of the smaller set is shared with the larger set, privately in your browser.
Enter two sets separated by commas, semicolons, or new lines. Spaces within an item are preserved; surrounding spaces and empty entries are ignored. Matching is case-sensitive and duplicates count once. Both sets must contain at least one item. The calculation runs locally in your browser; your values are not uploaded or stored.
How the overlap coefficient works
The Szymkiewicz–Simpson overlap coefficient is |A ∩ B| / min(|A|, |B|), using unique items. It ranges from 0 for disjoint sets to 1 when either set is a subset of the other. For A = apple, banana and B = apple, banana, cherry, the overlap coefficient is 1 even though the sets are not identical. Jaccard similarity is 2/3 and Dice similarity is 4/5 for that example. For two sets of three items with two shared items, overlap is 2/3. Both sets must be nonempty because an empty set gives a zero denominator. The reported dissimilarity is 1 minus overlap; it is not a metric and a zero value does not imply identical sets. Matching is case-sensitive after trimming surrounding whitespace; duplicates count once. Separate items with commas, semicolons or newlines. Spaces inside items are preserved; quoted CSV delimiters are not supported. Each set supports 10000 entries including duplicates and 200000 characters. Results display up to 12 significant digits and run entirely in your browser.
Frequently Asked Questions
Everything you need to know about this tool, how it works, and privacy.
How is the overlap coefficient calculated?
Divide the unique intersection size by the smaller unique set size. Two shared items between sets of sizes two and three give 2/2 = 1, or 100%.
Does a coefficient of 1 mean the sets are identical?
No. It means that one set is a subset of the other. Jaccard and Dice similarity equal 1 only when the nonempty sets are identical.
How are empty sets handled?
Both sets must contain at least one item. If either is empty, the denominator is zero and this calculator reports the coefficient as undefined.
What input format and limits apply?
Separate items with commas, semicolons or newlines. Matching is case-sensitive; duplicates count once and surrounding whitespace is trimmed. Each set allows 10000 entries including duplicates and 200000 characters. Quoted CSV delimiters are not supported.
Is overlap dissimilarity a metric?
No. One minus the overlap coefficient is not a distance metric: distinct sets can have zero dissimilarity, and the triangle inequality can fail. All calculation stays in your browser.