{
  "id": 1152,
  "title": "lmer and caret package in R",
  "url": "/competitions/WhatDoYouKnow/discussion/1152",
  "author_name": "",
  "post_date": "2011-12-13T19:06:13.430Z",
  "votes": null,
  "comment_count": 2,
  "views": 4122,
  "content": "<p>I'm very fond of using the caret package in R for building models.</p>\r\n<p>But despite the large number of supported algorithms, mixed effect models from the 'lme4' package aren't supported.</p>\r\n<p>Does anyone know if it is programmatically difficult to add support for this to caret? I'm tempted to contact the author and offer help.</p>\r\n<p>In the meantime, I suppose all of you are depending on kaggle for evaluating the goodness of your models. I really like evaluating a model using a test set on my own. Just curious if anyone else is in a similar situation.</p>",
  "messages": [
    {
      "id": "7104",
      "postDate": "12/13/2011 19:06:13",
      "content": "<p>I'm very fond of using the caret package in R for building models.</p>\r\n<p>But despite the large number of supported algorithms, mixed effect models from the 'lme4' package aren't supported.</p>\r\n<p>Does anyone know if it is programmatically difficult to add support for this to caret? I'm tempted to contact the author and offer help.</p>\r\n<p>In the meantime, I suppose all of you are depending on kaggle for evaluating the goodness of your models. I really like evaluating a model using a test set on my own. Just curious if anyone else is in a similar situation.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "7334",
      "postDate": "12/19/2011 14:44:05",
      "content": "<p>There's no prediction method for models built with lme4. To get caret to play nice, you'll have to hand code a prediction method, which isn't easy. (You can have lme4 give you the coefficients.)</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "7722",
      "postDate": "01/06/2012 17:06:23",
      "content": "<p>You can use &quot;custom&quot; methods in the latest version of caret. You can read more about this on page 40 of the &quot;Model Building&quot; vignette:<br>\r\nhttp://cran.r-project.org/web/packages/caret/vignettes/caretTrain.pdf</p>\r\n<p>As Shea noted, you'll need to hand code a prediction method for lme4.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 7334,
      "author_name": "biasvariance",
      "author_url": "",
      "post_date": "12/19/2011 14:44:05",
      "content": "<p>There's no prediction method for models built with lme4. To get caret to play nice, you'll have to hand code a prediction method, which isn't easy. (You can have lme4 give you the coefficients.)</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 7722,
      "author_name": "zachmayer",
      "author_url": "",
      "post_date": "01/06/2012 17:06:23",
      "content": "<p>You can use &quot;custom&quot; methods in the latest version of caret. You can read more about this on page 40 of the &quot;Model Building&quot; vignette:<br>\r\nhttp://cran.r-project.org/web/packages/caret/vignettes/caretTrain.pdf</p>\r\n<p>As Shea noted, you'll need to hand code a prediction method for lme4.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "7104": "",
    "7334": "",
    "7722": ""
  },
  "source": "meta"
}