{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifv7s2ijqpkyhru6j5xlql4c3hm4gtlbxouhia6rjju3ltm6u447i",
    "uri": "at://did:plc:wwyqal4cnqhuwyacdj7rqq3n/app.bsky.feed.post/3mjvmi77q7im2"
  },
  "path": "/t/risk-factor-evaluation-in-a-small-surgical-sample-n-20-events-6/28714#post_2",
  "publishedAt": "2026-04-19T12:49:11.000Z",
  "site": "https://discourse.datamethods.org",
  "tags": [
    "this"
  ],
  "textContent": "It is mathematically impossible to assess differences when there are 6 events. That’s because you cannot even estimate risk in your situation if there are **no** predictors, i.e., you can’t even estimate the intercept in a logistic model were all slopes known to be zero. See this. So this is a futile project, unfortunately.\n\nWhen doing penalization empirically (i.e., when not specifying a prior distribution to a Bayesian model) the sample size required to choose the right penalty can be quite large. It’s a lose-lose situation unfortunately.\n\nThe best you can do is to report a Wilson 0.95 confidence interval for the unknown outcome probability assuming homogeneous risk, which is [0.15, 0.52]. The point estimate of 0.3 is not meaningful. To nail down the average risk to 0.15 - 0.52 means we don’t know very much.",
  "title": "Risk factor evaluation in a small surgical sample (N=20, Events=6)"
}