{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibunjbm5o7mvr76dra43kcminpckjdkclr3vqzb4c6nbtblkeehgq",
    "uri": "at://did:plc:wwyqal4cnqhuwyacdj7rqq3n/app.bsky.feed.post/3mhvch26vyso2"
  },
  "path": "/t/biomarker-evaluation-c-statistic-auc-and-alternatives/6956?page=2#post_36",
  "publishedAt": "2026-03-25T06:46:24.000Z",
  "site": "https://discourse.datamethods.org",
  "tags": [
    "predictionperformancediscrimination.netlify.app",
    "discrimination"
  ],
  "textContent": "The difference between c-index of 0.72/0.70 means that the first model has 2% higher chance to guess the event in an imaginary game that samples one event and one non-event from the validated data.\n\nThe real issue is not the interpretability, but the relevance for decision making.\n\nConsidering new biomarkers must come with cost, c-index can’t help you with these kind of decisions.\n\nPS: That’s my attempt to explain c-index (and why I don’t like “area-under-curve” interpertation):\n\npredictionperformancediscrimination.netlify.app\n\n### discrimination",
  "title": "Biomarker evaluation - c-statistic (AUC) and alternatives"
}