{
  "id": 4128,
  "title": "Help With Logit Model",
  "url": "/competitions/icdar2013-gender-prediction-from-handwriting/discussion/4128",
  "author_name": "",
  "post_date": "2013-03-29T04:31:09.853Z",
  "votes": null,
  "comment_count": 2,
  "views": 2102,
  "content": "<p>Hi all. I'm having troble getting output from a logit model. Everytime I run glm() I get a combination of coefficients that are redicuolusly big (order 10^7) and NAs (usually beginning at&nbsp;directions_hist1a2a3a4_40[4]). I have eliminated variables that are\r\n &lt;.001 in more than 50% of cases, transformed the data by (x-avg(x))/sd(x), all to no avail. I really just need to get the benchmark model to work properly and I'll be good to go, but for some reason no matter what I do there are NA values in the model. Anyone\r\n have any advice?</p>\r\n<p>Thanks in advance,</p>\r\n<p>Pdubbs</p>",
  "messages": [
    {
      "id": "21796",
      "postDate": "03/29/2013 04:31:09",
      "content": "<p>Hi all. I'm having troble getting output from a logit model. Everytime I run glm() I get a combination of coefficients that are redicuolusly big (order 10^7) and NAs (usually beginning at&nbsp;directions_hist1a2a3a4_40[4]). I have eliminated variables that are\r\n &lt;.001 in more than 50% of cases, transformed the data by (x-avg(x))/sd(x), all to no avail. I really just need to get the benchmark model to work properly and I'll be good to go, but for some reason no matter what I do there are NA values in the model. Anyone\r\n have any advice?</p>\r\n<p>Thanks in advance,</p>\r\n<p>Pdubbs</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "21845",
      "postDate": "03/29/2013 23:50:57",
      "content": "<p>did you see this thread: http://www.kaggle.com/c/icdar2013-gender-prediction-from-handwriting/forums/t/4059/hints-to-improve-the-results-using-only-the-features-provided</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "22343",
      "postDate": "04/07/2013 03:21:44",
      "content": "<p>I'm still fighting with my logit, but that was very hepful. Thanks, Sashi!</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 21845,
      "author_name": "sashikanthdareddy",
      "author_url": "",
      "post_date": "03/29/2013 23:50:57",
      "content": "<p>did you see this thread: http://www.kaggle.com/c/icdar2013-gender-prediction-from-handwriting/forums/t/4059/hints-to-improve-the-results-using-only-the-features-provided</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 22343,
      "author_name": "pdubbs",
      "author_url": "",
      "post_date": "04/07/2013 03:21:44",
      "content": "<p>I'm still fighting with my logit, but that was very hepful. Thanks, Sashi!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "21796": "",
    "21845": "",
    "22343": ""
  },
  "source": "meta"
}