# A/B Test Significance Calculator (Two-Proportion Z-Test)

> A/B Test Significance Calculator (Two-Proportion Z-Test) is a paid API for AI agents from api.agentstools.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Computes A/B test statistical significance using a two-proportion z-test, returning observed lift, z-score, two-sided p-value, confidence interval on the lift, minimum detectable effect, and sample-size sufficiency.

## Facts

- Endpoint: POST https://api.agentstools.dev/marketing/experiment
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/a-b-test-significance-calculator-two-proportion-z-test-9eb400e6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_IlWtfIXUOqRjiLTN8WFmo

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability a-b-test-significance-calculator-two-proportion-z-test-9eb400e6 -d '<json body>'
```

Example prompt: My control group had 5,200 visitors with 312 conversions, and my variant had 5,100 visitors with 357 conversions — run a two-proportion z-test at 95% confidence and tell me if the lift is statistically significant, what the p-value is, and whether my sample size is sufficient.

## When to prefer this

Choose this endpoint when you need a fast, pure-computation statistical significance check for a two-group proportion experiment (e.g. conversion rates, click-through rates) without setting up a local stats library. It is ideal for AI agents that need to interpret A/B test results on the fly, check sample-size sufficiency before declaring a winner, or compute MDE for experiment planning — all with no side effects and deterministic results from your inputs alone.

## Known failure modes

- Missing or zero sample sizes cause division errors or invalid z-score computation
- Conversion counts exceeding sample size return a validation error
- Extremely small sample sizes may produce unreliable MDE or power estimates
- Invalid confidence level values (outside 0–1 or not a recognized percentage) return an error
- Network timeout or service unavailability returns a 5xx error

## How this service works

A/B test significance with a two-proportion z-test: observed lift, z-score, two-sided p-value, confidence interval on the lift, minimum detectable effect, and sample-size sufficiency. Pure computation over your inputs.

## Output

Returns a JSON object containing: the observed lift (percentage difference between variant and control conversion rates), the z-score, a two-sided p-value, a confidence interval (lower and upper bounds) on the lift, the minimum detectable effect given the sample sizes, and a boolean or flag indicating whether the sample size is sufficient to draw reliable conclusions.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "a": {
   "type": "object",
   "description": "Control arm with conversions and visitors"
  },
  "b": {
   "type": "object",
   "description": "Variant arm with conversions and visitors"
  },
  "alpha": {
   "type": "number",
   "description": "Significance level, default 0.05"
  },
  "power": {
   "type": "number",
   "description": "Target power for sample-size math, default 0.8"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/a-b-test-significance-calculator-two-proportion-z-test-9eb400e6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentstools.dev](https://www.zero.xyz/host/api.agentstools.dev/llms.txt)