{
  "x402Version": 2,
  "id": 72361,
  "slug": "saylorinnovations-api-math-ab-test",
  "resource": "https://saylorinnovations.com/api/math/ab-test",
  "description": "A/B test significance from visitors and conversions - lift, z-score, p-value, confidence interval, winner and the sample size needed per variant",
  "type": "http",
  "serviceName": "Saylor Innovations Data Desk",
  "mimeType": "application/json",
  "resourceType": "API",
  "accepts": [
    {
      "scheme": "exact",
      "network": "eip155:8453",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "eip155:137",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0x3c499c542cEF5E3811e1192ce70d8cC03d5c3359",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "eip155:42161",
      "payTo": "0xA2A8dF0f7CaaBEa4e120a2568118f141569fc8aa",
      "asset": "0xaf88d065e77c8cC2239327C5EDb3A432268e5831",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "Es9vMFrzaCERmJfrF4H2FYD4KCoNkY11McCe8BenwNYB",
      "amount": "10000",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    },
    {
      "scheme": "exact",
      "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
      "payTo": "7LSjfrJf8fNsB8VA9u7N3WEn25smQLpob3SvyUvXacy7",
      "asset": "So11111111111111111111111111111111111111112",
      "amount": "95830",
      "amountUsd": 0.01,
      "maxTimeoutSeconds": 120
    }
  ],
  "outputSchema": {
    "type": "object",
    "properties": {
      "variant_a": {
        "type": "object",
        "properties": {
          "visitors": {
            "description": "Visitors in variant A",
            "type": [
              "number",
              "null"
            ]
          },
          "conversions": {
            "description": "Conversions in variant A",
            "type": [
              "number",
              "null"
            ]
          },
          "conversion_rate_percent": {
            "type": [
              "number",
              "null"
            ],
            "description": "Conversion rate, as a percentage"
          }
        },
        "description": "Variant a"
      },
      "variant_b": {
        "type": "object",
        "properties": {
          "visitors": {
            "description": "Visitors in variant B",
            "type": [
              "number",
              "null"
            ]
          },
          "conversions": {
            "description": "Conversions in variant B",
            "type": [
              "number",
              "null"
            ]
          },
          "conversion_rate_percent": {
            "type": [
              "number",
              "null"
            ],
            "description": "Conversion rate, as a percentage"
          }
        },
        "description": "Variant b"
      },
      "relative_lift_percent": {
        "type": [
          "number",
          "null"
        ],
        "description": "Relative lift, as a percentage"
      },
      "z_score": {
        "type": "number",
        "description": "Z score"
      },
      "p_value": {
        "type": "number",
        "description": "P value"
      },
      "significant": {
        "type": "boolean",
        "description": "True when the p-value is below alpha"
      },
      "winner": {
        "type": "string",
        "description": "Better variant when significant, otherwise null"
      },
      "confidence_interval_difference": {
        "type": "object",
        "description": "Confidence interval difference"
      },
      "sample_size_per_variant_to_detect_observed_effect": {
        "type": [
          "number",
          "null"
        ],
        "description": "Sample size per variant to detect observed effect"
      },
      "advice": {
        "type": "string",
        "description": "The advice text"
      },
      "note": {
        "type": "string",
        "description": "Caveat or context for reading the result"
      },
      "source": {
        "type": "string",
        "description": "Data source the values come from"
      },
      "alpha": {
        "description": "Significance threshold used",
        "type": [
          "number",
          "null"
        ]
      },
      "underpowered": {
        "description": "True when the sample is too small to detect the observed lift reliably",
        "type": [
          "boolean",
          "null"
        ]
      },
      "absolute_difference_points": {
        "type": [
          "number",
          "null"
        ],
        "description": "Absolute difference points"
      },
      "probability_b_beats_a_approx": {
        "type": [
          "number",
          "null"
        ],
        "description": "Probability b beats a approx"
      },
      "current_sample_per_variant": {
        "type": [
          "number",
          "null"
        ],
        "description": "Current sample per variant"
      }
    },
    "required": [
      "variant_a",
      "variant_b",
      "p_value",
      "significant"
    ]
  },
  "extensions": {
    "bazaar": {
      "info": {
        "input": {
          "type": "http",
          "method": "GET",
          "queryParams": {
            "a_conversions": "250",
            "a_visitors": "5000",
            "b_conversions": "295",
            "b_visitors": "5000"
          }
        },
        "output": {
          "type": "json",
          "example": {
            "variant_a": {
              "visitors": 5000,
              "conversions": 250,
              "conversion_rate_percent": 5
            },
            "variant_b": {
              "visitors": 5000,
              "conversions": 295,
              "conversion_rate_percent": 5.9
            },
            "absolute_difference_points": 0.9,
            "relative_lift_percent": 18,
            "z_score": 1.982,
            "p_value": 0.04744,
            "alpha": 0.05,
            "significant": true,
            "winner": "B",
            "confidence_interval_difference": {
              "level": "95%",
              "low_points": 0.01,
              "high_points": 1.79
            },
            "probability_b_beats_a_approx": 0.9763,
            "sample_size_per_variant_to_detect_observed_effect": 9983,
            "current_sample_per_variant": 5000,
            "underpowered": true,
            "advice": "result is statistically significant at the chosen alpha; check it holds for a full business cycle before shipping",
            "note": "Two-sided two-proportion z-test with a pooled standard error for the p-value and an unpooled interval for the difference. Do not stop a test early just because it crosses significance (peeking inflates false positives); this assumes a fixed sample size.",
            "source": "two-proportion z-test"
          }
        }
      },
      "schema": {
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "type": "object",
        "properties": {
          "input": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "http"
              },
              "method": {
                "type": "string",
                "enum": [
                  "GET"
                ]
              },
              "queryParams": {
                "type": "object",
                "properties": {
                  "a_conversions": {
                    "type": "string",
                    "description": "Conversions in A"
                  },
                  "a_visitors": {
                    "type": "string",
                    "description": "Visitors in variant A"
                  },
                  "b_conversions": {
                    "type": "string",
                    "description": "Conversions in B"
                  },
                  "b_visitors": {
                    "type": "string",
                    "description": "Visitors in variant B"
                  }
                },
                "required": [
                  "a_conversions",
                  "a_visitors",
                  "b_conversions",
                  "b_visitors"
                ]
              }
            },
            "required": [
              "type",
              "method"
            ],
            "additionalProperties": false
          },
          "output": {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "json"
              },
              "example": {
                "type": "object",
                "properties": {
                  "variant_a": {
                    "type": "object",
                    "properties": {
                      "visitors": {
                        "description": "Visitors in variant A",
                        "type": [
                          "number",
                          "null"
                        ]
                      },
                      "conversions": {
                        "description": "Conversions in variant A",
                        "type": [
                          "number",
                          "null"
                        ]
                      },
                      "conversion_rate_percent": {
                        "type": [
                          "number",
                          "null"
                        ],
                        "description": "Conversion rate, as a percentage"
                      }
                    },
                    "description": "Variant a"
                  },
                  "variant_b": {
                    "type": "object",
                    "properties": {
                      "visitors": {
                        "description": "Visitors in variant B",
                        "type": [
                          "number",
                          "null"
                        ]
                      },
                      "conversions": {
                        "description": "Conversions in variant B",
                        "type": [
                          "number",
                          "null"
                        ]
                      },
                      "conversion_rate_percent": {
                        "type": [
                          "number",
                          "null"
                        ],
                        "description": "Conversion rate, as a percentage"
                      }
                    },
                    "description": "Variant b"
                  },
                  "relative_lift_percent": {
                    "type": [
                      "number",
                      "null"
                    ],
                    "description": "Relative lift, as a percentage"
                  },
                  "z_score": {
                    "type": "number",
                    "description": "Z score"
                  },
                  "p_value": {
                    "type": "number",
                    "description": "P value"
                  },
                  "significant": {
                    "type": "boolean",
                    "description": "True when the p-value is below alpha"
                  },
                  "winner": {
                    "type": "string",
                    "description": "Better variant when significant, otherwise null"
                  },
                  "confidence_interval_difference": {
                    "type": "object",
                    "description": "Confidence interval difference"
                  },
                  "sample_size_per_variant_to_detect_observed_effect": {
                    "type": [
                      "number",
                      "null"
                    ],
                    "description": "Sample size per variant to detect observed effect"
                  },
                  "advice": {
                    "type": "string",
                    "description": "The advice text"
                  },
                  "note": {
                    "type": "string",
                    "description": "Caveat or context for reading the result"
                  },
                  "source": {
                    "type": "string",
                    "description": "Data source the values come from"
                  },
                  "alpha": {
                    "description": "Significance threshold used",
                    "type": [
                      "number",
                      "null"
                    ]
                  },
                  "underpowered": {
                    "description": "True when the sample is too small to detect the observed lift reliably",
                    "type": [
                      "boolean",
                      "null"
                    ]
                  },
                  "absolute_difference_points": {
                    "type": [
                      "number",
                      "null"
                    ],
                    "description": "Absolute difference points"
                  },
                  "probability_b_beats_a_approx": {
                    "type": [
                      "number",
                      "null"
                    ],
                    "description": "Probability b beats a approx"
                  },
                  "current_sample_per_variant": {
                    "type": [
                      "number",
                      "null"
                    ],
                    "description": "Current sample per variant"
                  }
                },
                "required": [
                  "variant_a",
                  "variant_b",
                  "p_value",
                  "significant"
                ]
              }
            },
            "required": [
              "type"
            ]
          }
        },
        "required": [
          "input"
        ]
      }
    }
  },
  "tags": [
    "ab test significance calculator",
    "is variant b better than a",
    "conversion rate lift p value",
    "sample size for an ab test",
    "confidence interval"
  ],
  "sourceHost": "saylorinnovations.com",
  "lastUpdated": "2026-10-26T22:14:01.937Z",
  "quality": {},
  "metadata": {
    "serviceName": "Saylor Innovations Data Desk",
    "method": "GET",
    "mimeType": "application/json",
    "inputSchema": {
      "type": "object",
      "properties": {
        "a_conversions": {
          "type": "string",
          "description": "Conversions in A"
        },
        "a_visitors": {
          "type": "string",
          "description": "Visitors in variant A"
        },
        "b_conversions": {
          "type": "string",
          "description": "Conversions in B"
        },
        "b_visitors": {
          "type": "string",
          "description": "Visitors in variant B"
        }
      },
      "required": [
        "a_conversions",
        "a_visitors",
        "b_conversions",
        "b_visitors"
      ]
    },
    "exampleResponse": {
      "variant_a": {
        "visitors": 5000,
        "conversions": 250,
        "conversion_rate_percent": 5
      },
      "variant_b": {
        "visitors": 5000,
        "conversions": 295,
        "conversion_rate_percent": 5.9
      },
      "absolute_difference_points": 0.9,
      "relative_lift_percent": 18,
      "z_score": 1.982,
      "p_value": 0.04744,
      "alpha": 0.05,
      "significant": true,
      "winner": "B",
      "confidence_interval_difference": {
        "level": "95%",
        "low_points": 0.01,
        "high_points": 1.79
      },
      "probability_b_beats_a_approx": 0.9763,
      "sample_size_per_variant_to_detect_observed_effect": 9983,
      "current_sample_per_variant": 5000,
      "underpowered": true,
      "advice": "result is statistically significant at the chosen alpha; check it holds for a full business cycle before shipping",
      "note": "Two-sided two-proportion z-test with a pooled standard error for the p-value and an unpooled interval for the difference. Do not stop a test early just because it crosses significance (peeking inflates false positives); this assumes a fixed sample size.",
      "source": "two-proportion z-test"
    },
    "parameterLocation": "query",
    "extensions": {
      "bazaar": {
        "info": {
          "input": {
            "type": "http",
            "method": "GET",
            "queryParams": {
              "a_conversions": "250",
              "a_visitors": "5000",
              "b_conversions": "295",
              "b_visitors": "5000"
            }
          },
          "output": {
            "type": "json",
            "example": {
              "variant_a": {
                "visitors": 5000,
                "conversions": 250,
                "conversion_rate_percent": 5
              },
              "variant_b": {
                "visitors": 5000,
                "conversions": 295,
                "conversion_rate_percent": 5.9
              },
              "absolute_difference_points": 0.9,
              "relative_lift_percent": 18,
              "z_score": 1.982,
              "p_value": 0.04744,
              "alpha": 0.05,
              "significant": true,
              "winner": "B",
              "confidence_interval_difference": {
                "level": "95%",
                "low_points": 0.01,
                "high_points": 1.79
              },
              "probability_b_beats_a_approx": 0.9763,
              "sample_size_per_variant_to_detect_observed_effect": 9983,
              "current_sample_per_variant": 5000,
              "underpowered": true,
              "advice": "result is statistically significant at the chosen alpha; check it holds for a full business cycle before shipping",
              "note": "Two-sided two-proportion z-test with a pooled standard error for the p-value and an unpooled interval for the difference. Do not stop a test early just because it crosses significance (peeking inflates false positives); this assumes a fixed sample size.",
              "source": "two-proportion z-test"
            }
          }
        },
        "schema": {
          "$schema": "https://json-schema.org/draft/2020-12/schema",
          "type": "object",
          "properties": {
            "input": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "http"
                },
                "method": {
                  "type": "string",
                  "enum": [
                    "GET"
                  ]
                },
                "queryParams": {
                  "type": "object",
                  "properties": {
                    "a_conversions": {
                      "type": "string",
                      "description": "Conversions in A"
                    },
                    "a_visitors": {
                      "type": "string",
                      "description": "Visitors in variant A"
                    },
                    "b_conversions": {
                      "type": "string",
                      "description": "Conversions in B"
                    },
                    "b_visitors": {
                      "type": "string",
                      "description": "Visitors in variant B"
                    }
                  },
                  "required": [
                    "a_conversions",
                    "a_visitors",
                    "b_conversions",
                    "b_visitors"
                  ]
                }
              },
              "required": [
                "type",
                "method"
              ],
              "additionalProperties": false
            },
            "output": {
              "type": "object",
              "properties": {
                "type": {
                  "type": "string",
                  "const": "json"
                },
                "example": {
                  "type": "object",
                  "properties": {
                    "variant_a": {
                      "type": "object",
                      "properties": {
                        "visitors": {
                          "description": "Visitors in variant A",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "conversions": {
                          "description": "Conversions in variant A",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "conversion_rate_percent": {
                          "type": [
                            "number",
                            "null"
                          ],
                          "description": "Conversion rate, as a percentage"
                        }
                      },
                      "description": "Variant a"
                    },
                    "variant_b": {
                      "type": "object",
                      "properties": {
                        "visitors": {
                          "description": "Visitors in variant B",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "conversions": {
                          "description": "Conversions in variant B",
                          "type": [
                            "number",
                            "null"
                          ]
                        },
                        "conversion_rate_percent": {
                          "type": [
                            "number",
                            "null"
                          ],
                          "description": "Conversion rate, as a percentage"
                        }
                      },
                      "description": "Variant b"
                    },
                    "relative_lift_percent": {
                      "type": [
                        "number",
                        "null"
                      ],
                      "description": "Relative lift, as a percentage"
                    },
                    "z_score": {
                      "type": "number",
                      "description": "Z score"
                    },
                    "p_value": {
                      "type": "number",
                      "description": "P value"
                    },
                    "significant": {
                      "type": "boolean",
                      "description": "True when the p-value is below alpha"
                    },
                    "winner": {
                      "type": "string",
                      "description": "Better variant when significant, otherwise null"
                    },
                    "confidence_interval_difference": {
                      "type": "object",
                      "description": "Confidence interval difference"
                    },
                    "sample_size_per_variant_to_detect_observed_effect": {
                      "type": [
                        "number",
                        "null"
                      ],
                      "description": "Sample size per variant to detect observed effect"
                    },
                    "advice": {
                      "type": "string",
                      "description": "The advice text"
                    },
                    "note": {
                      "type": "string",
                      "description": "Caveat or context for reading the result"
                    },
                    "source": {
                      "type": "string",
                      "description": "Data source the values come from"
                    },
                    "alpha": {
                      "description": "Significance threshold used",
                      "type": [
                        "number",
                        "null"
                      ]
                    },
                    "underpowered": {
                      "description": "True when the sample is too small to detect the observed lift reliably",
                      "type": [
                        "boolean",
                        "null"
                      ]
                    },
                    "absolute_difference_points": {
                      "type": [
                        "number",
                        "null"
                      ],
                      "description": "Absolute difference points"
                    },
                    "probability_b_beats_a_approx": {
                      "type": [
                        "number",
                        "null"
                      ],
                      "description": "Probability b beats a approx"
                    },
                    "current_sample_per_variant": {
                      "type": [
                        "number",
                        "null"
                      ],
                      "description": "Current sample per variant"
                    }
                  },
                  "required": [
                    "variant_a",
                    "variant_b",
                    "p_value",
                    "significant"
                  ]
                }
              },
              "required": [
                "type"
              ]
            }
          },
          "required": [
            "input"
          ]
        }
      }
    },
    "examples": [
      {
        "label": "Unpaid discovery call",
        "method": "GET",
        "url": "https://saylorinnovations.com/api/math/ab-test?a_visitors=5000&a_conversions=250&b_visitors=5000&b_conversions=295",
        "expectedStatus": 402
      }
    ],
    "cacheTtlSeconds": 0,
    "capabilities": [],
    "noAccountRequired": true,
    "noApiKeyRequired": true,
    "sideEffects": "Paid calls settle the advertised payment; see the provider contract for execution behavior.",
    "payment": {
      "protocol": "x402",
      "settlement": "direct-to-provider"
    },
    "provider": {
      "name": "Saylor Innovations",
      "host": "saylorinnovations.com",
      "manifestUrl": "https://saylorinnovations.com/.well-known/x402.json"
    }
  },
  "liveness": {
    "reliability": null
  },
  "verified": true,
  "featured": false,
  "provider": {
    "host": "saylorinnovations.com",
    "manifest_name": "Saylor Innovations Knowledge Base",
    "source": "submitted",
    "source_manifest_url": "https://saylorinnovations.com/.well-known/x402.json",
    "submitted_at": "2026-10-26T05:52:02.113Z"
  },
  "exampleResponse": {
    "variant_a": {
      "visitors": 0,
      "conversions": 0,
      "conversion_rate_percent": 0
    },
    "variant_b": {
      "visitors": 0,
      "conversions": 0,
      "conversion_rate_percent": 0
    },
    "relative_lift_percent": 0,
    "z_score": 0,
    "p_value": 0,
    "significant": true,
    "winner": "string",
    "confidence_interval_difference": {},
    "sample_size_per_variant_to_detect_observed_effect": 0,
    "advice": "string",
    "note": "string",
    "source": "string",
    "alpha": 0,
    "underpowered": true,
    "absolute_difference_points": 0,
    "probability_b_beats_a_approx": 0,
    "current_sample_per_variant": 0
  }
}