{
  "id": 80190,
  "title": "Distribution of Time Between Earthquakes",
  "url": "/competitions/LANL-Earthquake-Prediction/discussion/80190",
  "author_name": "",
  "post_date": "2019-02-11T15:39:41.807717100Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello,</p>\n\n<p>Is a good prior distribution for the time between earthquakes for these experiments known or commonly used?  If so, what is that distribution?</p>\n\n<p>Is the exponential failure distribution commonly applied to these earthquakes?</p>\n\n<p>Thanks,\nAth</p>",
  "messages": [
    {
      "id": "469644",
      "postDate": "02/11/2019 15:39:41",
      "content": "<p>Hello,</p>\n\n<p>Is a good prior distribution for the time between earthquakes for these experiments known or commonly used?  If so, what is that distribution?</p>\n\n<p>Is the exponential failure distribution commonly applied to these earthquakes?</p>\n\n<p>Thanks,\nAth</p>",
      "rawMarkdown": "Hello,\n\nIs a good prior distribution for the time between earthquakes for these experiments known or commonly used?  If so, what is that distribution?\n\nIs the exponential failure distribution commonly applied to these earthquakes?\n\nThanks,\nAth",
      "votes": null
    },
    {
      "id": "473540",
      "postDate": "02/18/2019 06:47:48",
      "content": "<p>Not an expert on earthquakes, but seems that exponential failure distribution could be a fit. It assumes Poisson point process and that is something that is used for earth quakes. Also from Wiki:</p>\n\n<p>\"The Poisson point process is often defined on the real line, where it can be considered as a stochastic process. In this setting, it is used, for example, in queueing theory to model random events, such as the arrival of customers at a store, phone calls at an exchange or occurrence of <strong>earthquakes</strong>, distributed in time\"</p>\n\n<p>Out of curiosity,  are you going with some type of Bayesian approach where you try to predict the distribution at the end of the 150_000 samples? </p>",
      "rawMarkdown": "Not an expert on earthquakes, but seems that exponential failure distribution could be a fit. It assumes Poisson point process and that is something that is used for earth quakes. Also from Wiki:\n\n\"The Poisson point process is often defined on the real line, where it can be considered as a stochastic process. In this setting, it is used, for example, in queueing theory to model random events, such as the arrival of customers at a store, phone calls at an exchange or occurrence of **earthquakes**, distributed in time\"\n\nOut of curiosity,  are you going with some type of Bayesian approach where you try to predict the distribution at the end of the 150_000 samples?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 473540,
      "author_name": "peterdekkers101",
      "author_url": "",
      "post_date": "02/18/2019 06:47:48",
      "content": "<p>Not an expert on earthquakes, but seems that exponential failure distribution could be a fit. It assumes Poisson point process and that is something that is used for earth quakes. Also from Wiki:</p>\n\n<p>\"The Poisson point process is often defined on the real line, where it can be considered as a stochastic process. In this setting, it is used, for example, in queueing theory to model random events, such as the arrival of customers at a store, phone calls at an exchange or occurrence of <strong>earthquakes</strong>, distributed in time\"</p>\n\n<p>Out of curiosity,  are you going with some type of Bayesian approach where you try to predict the distribution at the end of the 150_000 samples? </p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "469644": "Hello,\n\nIs a good prior distribution for the time between earthquakes for these experiments known or commonly used?  If so, what is that distribution?\n\nIs the exponential failure distribution commonly applied to these earthquakes?\n\nThanks,\nAth",
    "473540": "Not an expert on earthquakes, but seems that exponential failure distribution could be a fit. It assumes Poisson point process and that is something that is used for earth quakes. Also from Wiki:\n\n\"The Poisson point process is often defined on the real line, where it can be considered as a stochastic process. In this setting, it is used, for example, in queueing theory to model random events, such as the arrival of customers at a store, phone calls at an exchange or occurrence of **earthquakes**, distributed in time\"\n\nOut of curiosity,  are you going with some type of Bayesian approach where you try to predict the distribution at the end of the 150_000 samples?"
  },
  "source": "meta"
}