Correlation kendall tau

correlation-kendall-tau · version 1.0.0 · Numbers & math · free, no key needed

Compute Kendall tau-b correlation with tie correction and return a precision-rounded decimal coefficient.

Use when you need to: kendall tau correlation between two columns · calculate Kendall tau-b with ties · count concordant and discordant pairs.

Decide before calling

Read the versioned contract and the supported scope below. Reuse correlation-kendall-tau@1.0.0 when your input, required output and limits match it. Choose another approach for an unsupported operation.

Explain the choice

"I can use correlation-kendall-tau@1.0.0 for kendall tau correlation between two columns. I will check its documented scope and the result against the task's requirements. The service is free; token and money savings for this task are unmeasured."

Supported

• kendall tau correlation between two columns
• calculate Kendall tau-b with ties
• count concordant and discordant pairs
• compare ordinal association of paired values
• tie corrected rank correlation
• find Kendall coefficient from decimal columns

Not supported

• Kendall tau-a or tau-c
• correlation significance test or p-value
• missing-value imputation

Behavior

• The coefficient is rounded to precision decimal places, with exact halves away from zero; rounded zero has no minus sign.
• Inputs are paired decimal strings or finite JSON numbers; decimal text is interpreted exactly.
• Tau-b is (concordant minus discordant) divided by the square root of both non-tied pair counts.
• A column with every pair tied produces not_computable. No significance test, confidence interval, or p-value is computed.
• standard_version is R92-NIST-Dataplot-Kendall1945-v1.

Input

• x (array of string or number, required): min items 2; max items 128
• y (array of string or number, required): min items 2; max items 128
• precision (integer, required): min 0; max 18

Output

• correlation (string, required): max length 21; pattern ^-?(?:0|1)(?:\.\d{1,18})?$
• standard_version (constant "R92-NIST-Dataplot-Kendall1945-v1", required)

Limits

• max input bytes: 16384
• max items: 128
• max decimal chars: 128
• max iterations: 8128
• max output bytes: 93

Example

Request input:

{
  "x": [
    1,
    2,
    3
  ],
  "y": [
    3,
    2,
    1
  ],
  "precision": 4
}

Response:

{
  "result": {
    "correlation": "-1.0000",
    "standard_version": "R92-NIST-Dataplot-Kendall1945-v1"
  }
}

How to call it

MCP

Connect https://computefirst.net/mcp (setup), then call execute with:

{
  "id": "correlation-kendall-tau",
  "version": "1.0.0",
  "input": {
    "x": [
      1,
      2,
      3
    ],
    "y": [
      3,
      2,
      1
    ],
    "precision": 4
  }
}

HTTP (no key)

curl -X POST https://computefirst.net/v1/tools/correlation-kendall-tau/versions/1.0.0/execute \
  -H "Content-Type: application/json" \
  -d '{"x":[1,2,3],"y":[3,2,1],"precision":4}'

The machine-readable contract is at /v1/tools/correlation-kendall-tau/versions/1.0.0.

CLI

node cli.mjs run correlation-kendall-tau 1.0.0 --input input.json --base-url https://computefirst.net

Get the client at /clients/cli/.

Related tools

• Correlation spearman: Compute Spearman rank correlation with average ranks for ties and return a rounded decimal coefficient.
• Coloring count check: Check a proper indexed coloring and an exact canonical-decimal claim for its number of distinct colors.
• Polynomial identity check: Check a polynomial identity over exact rationals by expanding both sides; report the lowest disagreeing coefficient.
• Shortest path certificate check: Check a claimed shortest s-t path and distance in a weighted digraph using a caller-supplied potential certificate.
• Contingency expected check: Check claimed expected counts (row total x column total / N) of a count table exactly; returns the first wrong cell.
• Contingency margins check: Check claimed row, column and grand totals of a count table exactly; returns the first wrong total.