{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreieuasiebj3m42wjupr2pbmg4vy5yrlu4rmoxqicxk2fbi44re36sq",
    "uri": "at://did:plc:wwyqal4cnqhuwyacdj7rqq3n/app.bsky.feed.post/3mhwy4523iwx2"
  },
  "path": "/t/best-model-reduction-approach-for-fine-gray-prediction-model/28678#post_1",
  "publishedAt": "2026-03-26T04:22:54.000Z",
  "site": "https://discourse.datamethods.org",
  "textContent": "Hello there,\n\nI am developing a Fine-Gray competing risks prediction model for dementia incidence (with death as the competing event) using population-based survey data linked to administrative health records. My full model contains 76 candidate predictor terms, including restricted cubic spline transformations and interaction terms.\n\nI am evaluating two approaches for model reduction to create a parsimonious model for clinical/public health use:\n\n  1. **Stepwise selection** (particularly Ambler)\n  2. **Penalized regression / shrinkage** (particularly LASSO)\n\n\n\nWhich of the two approaches above would be best recommended for my case? Or is there another approach which would be better?\n\nWould appreciate any feedback!\n\nThanks,\nRaf",
  "title": "Best model reduction approach for Fine-Gray prediction model"
}