{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigmik76huvqqny7l5psgvl2wujmtxq4rev5amiak46lia7cqx6hbu",
    "uri": "at://did:plc:wwyqal4cnqhuwyacdj7rqq3n/app.bsky.feed.post/3mfmbsaepwrz2"
  },
  "path": "/t/generalizability-vs-transportability-in-trials/28551?page=3#post_48",
  "publishedAt": "2026-02-24T13:15:10.000Z",
  "site": "https://discourse.datamethods.org",
  "tags": [
    "@Stephen"
  ],
  "textContent": "Fantastic discussion. I would like to not see the term _quantitative interaction_ applied as it has been above. Risk magnification does not represent any kind of interaction unless people insist on analyzing interaction on the wrong scale.\n\nA key problem with NNT can be reduced to misunderstandings of many statisticians on the simple 2\\times 2 table and what Pearson’s \\chi^2 test was designed for. Pearson’s test (and all of its variants) starts with an assumption that every patient in a treatment group has the same probability of the event. The same assumption is made by non-covariate-specific NNT. Likewise, the t test assumes that every patient within a treatment group has a measurement having a normal distribution with the same mean and variance as all other patients in the treatment group. These assumptions of outcome homogeneity make naive statistical calculations a lot less meaningful than researchers (including statisticians) assume, and invalidate uncertainty measures.\n\n@Stephen has written about some of Sackett’s errors.",
  "title": "Generalizability vs. Transportability in Trials"
}