{
  "status": "shipping",
  "advantages": [],
  "limitations": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-10-16",
  "slug": "interval-censoring",
  "term": "Interval-censoring",
  "aliases": [
    "Interval censored data",
    "Readout data"
  ],
  "definition": "Interval-censoring is incomplete event-time observation in which an event is known to have occurred within an interval but its exact time is unknown.",
  "note": "NIST distinguishes interval records from exact event times and right-censored follow-up. [nist-interval] In storage, a verified last-good observation L and first detected persistent corruption R can imply L < T <= R only when both observations concern the same content version and the verification covers the event. A schedule or whole-job completion time is not automatically a block-level last-good observation. Repair, overwrites, missed checks and detection limits require explicit treatment. The midpoint is an imputed time, not an observed onset. This application is an interpretation rule, not a fitted failure model. [hesela-interval]",
  "related": [
    "right-censoring",
    "informative-censoring",
    "latent-sector-error",
    "data-scrubbing",
    "mean-time-to-detection"
  ],
  "citations": [
    {
      "id": "nist-interval",
      "title": "NIST/SEMATECH e-Handbook: Censoring, readout or interval data.",
      "url": "https://www.itl.nist.gov/div898/handbook/apr/section1/apr131.htm",
      "accessed": "2026-10-16"
    },
    {
      "id": "hesela-interval",
      "title": "Hesela: Scrubbing inspection intervals and evidence bounds.",
      "url": "https://hesela.com/analyses/scrubbing-detection-not-durability/#inspection-intervals",
      "accessed": "2026-10-16"
    }
  ]
}