ATProto Browser

{
  "text": "We don't actually identify always takers and never takers. \n\nSo why in the mathematics of an instrumental variable analysis does our exposure (X) need to be binary?\n\nIf this truly is the DAG for IV regression shouldn't it be able to support continuous exposure or compliance? \n\n#stats",
  "$type": "app.bsky.feed.post",
  "embed": {
    "$type": "app.bsky.embed.images",
    "images": [
      {
        "alt": "",
        "image": {
          "$type": "blob",
          "ref": {
            "$link": "bafkreig4e6skolix24kiodysouheylfxjyybom26ewcarctsop4f3t7mrm"
          },
          "mimeType": "image/jpeg",
          "size": 48939
        },
        "aspectRatio": {
          "width": 850,
          "height": 384
        }
      }
    ]
  },
  "langs": [
    "en"
  ],
  "facets": [
    {
      "index": {
        "byteEnd": 284,
        "byteStart": 278
      },
      "features": [
        {
          "tag": "stats",
          "$type": "app.bsky.richtext.facet#tag"
        }
      ]
    }
  ],
  "createdAt": "2025-04-07T14:30:31.945Z"
}