{
  "id": 5134,
  "title": "train2 target answer is incorrect?",
  "url": "/competitions/cause-effect-pairs/discussion/5134",
  "author_name": "",
  "post_date": "2013-07-17T17:39:54.963Z",
  "votes": null,
  "comment_count": 4,
  "views": 1339,
  "content": "<p>target states that A causes B.</p>\r\n<p>Clearly, B causes A.</p>\r\n<p>Am I right?</p>",
  "messages": [
    {
      "id": "27374",
      "postDate": "07/17/2013 17:39:54",
      "content": "<p>target states that A causes B.</p>\r\n<p>Clearly, B causes A.</p>\r\n<p>Am I right?</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27403",
      "postDate": "07/18/2013 12:13:20",
      "content": "<p>[quote=Kevinh7777;27374]</p>\r\n<p>target states that A causes B.</p>\r\n<p>Clearly, B causes A.</p>\r\n<p>Am I right?</p>\r\n<p>[/quote]</p>\r\n<p>My above question is very important because</p>\r\n<p>http://www.causality.inf.ethz.ch/cause-effect.php?page=tasks</p>\r\n<p>states that we are interested in the TRUE relation between A and B, not an arbitrarily chosen correct answer.</p>\r\n<p></p>\r\n<p>A common understanding of the true relation between variables, rather than an arbitrarily decided one, is crucially important to this field of research being genuinely regarded by society.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27482",
      "postDate": "07/21/2013 07:42:21",
      "content": "<p>I agree with you in that training data should be corrected should there be a mistake.</p>\n<p>Having said that, train2's B is categorical and order of the values should mean nothing at all, which makes it less obvious whether B is really the cause of A...&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27558",
      "postDate": "07/23/2013 17:12:28",
      "content": "<p>Both train2 and train4 are artificial pairs so there is no doubt about the true causal direction. However, this does not mean that it is possible to infer it from data (because the noise, the finite sample and the particular functional relationship). I will not answer more questions about pairs of variables.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "27640",
      "postDate": "07/25/2013 07:59:56",
      "content": "<p>[quote=nor;27482]</p>\n<p>I agree with you in that training data should be corrected should there be a mistake.</p>\n<p>Having said that, train2's B is categorical and order of the values should mean nothing at all, which makes it less obvious whether B is really the cause of A...&nbsp;</p>\n<p>[/quote]</p>\n<p>It's obvious when they are plotted on a scatterchart that it is much more likely that B caused A, in a context such as manufacturing.</p>\n<p>It appears there is source code available that generated these pairs?</p>\n<p>Nor, can you email it to me?&nbsp; I may understand more about Isabelle's post then.&nbsp; Thanks.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 27403,
      "author_name": "kevinh7777",
      "author_url": "",
      "post_date": "07/18/2013 12:13:20",
      "content": "<p>[quote=Kevinh7777;27374]</p>\r\n<p>target states that A causes B.</p>\r\n<p>Clearly, B causes A.</p>\r\n<p>Am I right?</p>\r\n<p>[/quote]</p>\r\n<p>My above question is very important because</p>\r\n<p>http://www.causality.inf.ethz.ch/cause-effect.php?page=tasks</p>\r\n<p>states that we are interested in the TRUE relation between A and B, not an arbitrarily chosen correct answer.</p>\r\n<p></p>\r\n<p>A common understanding of the true relation between variables, rather than an arbitrarily decided one, is crucially important to this field of research being genuinely regarded by society.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 27482,
      "author_name": "nor33855",
      "author_url": "",
      "post_date": "07/21/2013 07:42:21",
      "content": "<p>I agree with you in that training data should be corrected should there be a mistake.</p>\n<p>Having said that, train2's B is categorical and order of the values should mean nothing at all, which makes it less obvious whether B is really the cause of A...&nbsp;</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 27558,
      "author_name": "iguyon",
      "author_url": "",
      "post_date": "07/23/2013 17:12:28",
      "content": "<p>Both train2 and train4 are artificial pairs so there is no doubt about the true causal direction. However, this does not mean that it is possible to infer it from data (because the noise, the finite sample and the particular functional relationship). I will not answer more questions about pairs of variables.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 27640,
      "author_name": "kevinh7777",
      "author_url": "",
      "post_date": "07/25/2013 07:59:56",
      "content": "<p>[quote=nor;27482]</p>\n<p>I agree with you in that training data should be corrected should there be a mistake.</p>\n<p>Having said that, train2's B is categorical and order of the values should mean nothing at all, which makes it less obvious whether B is really the cause of A...&nbsp;</p>\n<p>[/quote]</p>\n<p>It's obvious when they are plotted on a scatterchart that it is much more likely that B caused A, in a context such as manufacturing.</p>\n<p>It appears there is source code available that generated these pairs?</p>\n<p>Nor, can you email it to me?&nbsp; I may understand more about Isabelle's post then.&nbsp; Thanks.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "27374": "",
    "27403": "",
    "27482": "",
    "27558": "",
    "27640": ""
  },
  "source": "meta"
}