{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreid3jig6j7ojbyhdkeskmwcuvqpx75rcwkkk5snhbfk5evv6gpum6a",
    "uri": "at://did:plc:wwyqal4cnqhuwyacdj7rqq3n/app.bsky.feed.post/3mj5aaxe5e322"
  },
  "path": "/t/power-calculations-in-longitudinal-mixed-effects-from-two-measurements-to-three-measurements/28699#post_5",
  "publishedAt": "2026-04-10T08:46:17.000Z",
  "site": "https://discourse.datamethods.org",
  "textContent": "Thank you, Frank, once again. Please allow me to offer some pushback and ask a few further questions.\n\nFirst, please note that I am not referring to scenarios with over seven measurements, but rather specifically the transition from two to three.\n\nAdditionally, this does not apply exclusively to random effects but also to GEE.\n\nThe previous software also indicates that when moving from compound symmetry to AR(1), the power actually decreases.\n\nRegarding questions involving two, three, or four follow-up measurements: if I understood correctly, your preference would be for GLS or Markov models?\n\nIn those models, do you have to manually specify the correlation matrix during analysis, or does the models handle that automatically in the background?\n\nAlso, out of curiosity, do you believe GEE is better than linear mixed-effects models for parallel RCTs?",
  "title": "Power Calculations in Longitudinal Mixed Effects - from two measurements to three measurements"
}