{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreickemfb7ipcqeybtn52n4uzysylbgf5wutdmm53nevl3qy4pgz5ou",
    "uri": "at://did:plc:wwyqal4cnqhuwyacdj7rqq3n/app.bsky.feed.post/3miktpct73ee2"
  },
  "path": "/t/collider-in-rct-subgroup-analysis/28689#post_5",
  "publishedAt": "2026-04-02T13:41:36.000Z",
  "site": "https://discourse.datamethods.org",
  "tags": [
    "@Pavlos_Msaouel"
  ],
  "textContent": "arthur_albuquerque:\n\n> I noticed that stratifying by subgroup and including the T \\times S parameter could open a backdoor path in both interaction or effect modifier frameworks if an unobserved variable influences both T \\times S and the outcome:\n\nI’m still a bit confused.\n\n\nPeople who are part of the subgroup also have a higher/lower risk for the outcome than people not part of this subgroup, even if they are not given the treatment. That’s @Pavlos_Msaouel EGFR example. People from the subgroup also have a different relative treatment effect (on the scale of interest) when given treatment than people not in the subgroup.\n\nThe second DAG:\n\n\n\nBeing part of the subgroup tells us nothing about the risk of the outcome if no treatment is given. Under treatment it does.\n\n**This DAG is confusing me** :\n\n\nWhy is there an arrow from \\text{Unobserved} \\rightarrow \\text{T x S} ? We are not modeling the \\text{T x S} Interaction using U?\nI think this corresponds to this graph from Pavlos publication. But the above DAG would somehow lead me to think that people who are part of U and \\text{subgroup} have a different relative treatment effect than people who are part of \\text{subgroup} and not U?\n\nQuote from Epi paper which helps a bit:\n\n> It is possible that there are factors that influence the likelihood of both expo- sures occurring concurrently (marked by an arrow into the interaction E G node) and also influence disease risk (marked by an arrow into the disease D node); such a fac- tor would create a back-door path and this would be ex- plicitly visualized in the DAG (see Figure 2c). Continuing with our example of smoking (E), asbestos (G) and lung cancer (D), a potential confounder (C) would be a factor that increases the likelihood of both smoking and asbesto- sis exposure, such as socio-economic status. Although this back-door path could also be captured by arrows from C to both E and G if the E G node were omitted, the inter- action node prompts the researcher to think about factors that affect both exposures simultaneously.\n\nI’ll try to simulate some data to wrap my head around this.",
  "title": "Collider in RCT Subgroup Analysis"
}