Experimental browser for the Atmosphere
Coefficient plots are in! You see them all over. A while back, I heard someone argue that we should use smoothed CIs in our coefficient plots, like below. This aligns with Gelman's principle: the difference between “significant” & “not significant” is not statistically significant. Thoughts?
Apr 23, 2025, 7:24 PM
{ "uri": "at://did:plc:nkee2udfh3mazkqatimusiwm/app.bsky.feed.post/3lniwaxi2as26", "cid": "bafyreiazha3sarkehdzhqq4ih47zf2y73hdd5vx7uni6dcenfdrxk4ru2m", "value": { "text": "Coefficient plots are in! You see them all over.\n\nA while back, I heard someone argue that we should use smoothed CIs in our coefficient plots, like below.\n\nThis aligns with Gelman's principle: the difference between “significant” & “not significant” is not statistically significant.\n\nThoughts?", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.images", "images": [ { "alt": "", "image": { "$type": "blob", "ref": { "$link": "bafkreibtir7dc32pzpcoxymvpwjlwgn2erxje6cdbj2lju6zme3un7vk4q" }, "mimeType": "image/jpeg", "size": 254164 }, "aspectRatio": { "width": 1280, "height": 1280 } } ] }, "langs": [ "en" ], "createdAt": "2025-04-23T19:24:46.583Z" } }