{
  "id": 181198,
  "title": "What is the relation between Confidence and Percent?",
  "url": "/competitions/osic-pulmonary-fibrosis-progression/discussion/181198",
  "author_name": "",
  "post_date": "2020-09-07T23:41:09.682927300Z",
  "votes": null,
  "comment_count": 5,
  "views": 0,
  "content": "<p>I sometime saw the formula like this.</p>\n<p>𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)</p>\n<p>I couldn't understand the relation between Confidence and Percent.<br>\nCould someone explain that?<br>\nThank you for looking this discussion.</p>",
  "messages": [
    {
      "id": "1002218",
      "postDate": "09/07/2020 23:41:09",
      "content": "<p>I sometime saw the formula like this.</p>\n<p>𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)</p>\n<p>I couldn't understand the relation between Confidence and Percent.<br>\nCould someone explain that?<br>\nThank you for looking this discussion.</p>",
      "rawMarkdown": "I sometime saw the formula like this.\n\n𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)\n\nI couldn't understand the relation between Confidence and Percent.\nCould someone explain that?\nThank you for looking this discussion.",
      "votes": null
    },
    {
      "id": "1002381",
      "postDate": "09/08/2020 05:04:57",
      "content": "<h4>In brief</h4>\n<p>Confidence interval shows whether our assumed hypothesis fall in between or not.<br>\nand percentage is the probability which shows what is the probability of getting assumed hypothesis to be true.</p>\n<h5>for more <a href=\"https://www.bmj.com/about-bmj/resources-readers/publications/statistics-square-one/4-statements-probability-and-confiden\" target=\"_blank\">check this</a></h5>",
      "rawMarkdown": "#### In brief\nConfidence interval shows whether our assumed hypothesis fall in between or not.\nand percentage is the probability which shows what is the probability of getting assumed hypothesis to be true.\n##### for more [check this](https://www.bmj.com/about-bmj/resources-readers/publications/statistics-square-one/4-statements-probability-and-confiden)",
      "votes": null
    },
    {
      "id": "1003384",
      "postDate": "09/08/2020 22:37:39",
      "content": "<p>Thank you your comment.<br>\nYeah, I know confidence interval and percentage in statistics.<br>\nBut in this competition, “Percent” means this.</p>\n<p>“a computed field which approximates the patient's FVC as a percent of the typical FVC for a person of similar characteristics”</p>\n<p>I didn’t understand why we can calculate “Confidence” from this “Percent”.</p>",
      "rawMarkdown": "Thank you your comment.\nYeah, I know confidence interval and percentage in statistics.\nBut in this competition, “Percent” means this.\n\n“a computed field which approximates the patient's FVC as a percent of the typical FVC for a person of similar characteristics”\n\nI didn’t understand why we can calculate “Confidence” from this “Percent”.",
      "votes": null
    },
    {
      "id": "1003426",
      "postDate": "09/09/2020 00:51:05",
      "content": "<p>Are you assuming the confidence in the competition is referring to something else? So far my assumption is this is nothing different. </p>\n<p>\"Confidence levels are expressed as a percentage (for example, a 95% confidence level). It means that should you repeat an experiment or survey over and over again, 95 percent of the time your results will match the results you get from a population (in other words, your statistics would be sound!). Confidence intervals are your results and they are usually numbers. For example, here, for a specific group of features, we want to know FVC. You test your statistics at the 99 percent confidence level and get a confidence interval of (x,y). That means you think the FVC is between x and y You’re super confident (99% is a very high level!) that your results are sound, statistically.\" Correct me if I'm wrong.</p>",
      "rawMarkdown": "Are you assuming the confidence in the competition is referring to something else? So far my assumption is this is nothing different. \n\n\"Confidence levels are expressed as a percentage (for example, a 95% confidence level). It means that should you repeat an experiment or survey over and over again, 95 percent of the time your results will match the results you get from a population (in other words, your statistics would be sound!). Confidence intervals are your results and they are usually numbers. For example, here, for a specific group of features, we want to know FVC. You test your statistics at the 99 percent confidence level and get a confidence interval of (x,y). That means you think the FVC is between x and y You’re super confident (99% is a very high level!) that your results are sound, statistically.\" Correct me if I'm wrong.",
      "votes": null
    },
    {
      "id": "1007230",
      "postDate": "09/12/2020 00:38:34",
      "content": "<p>Thank you your comment.<br>\nI come to know this \"Confidence\" is equal to statistical definition.<br>\nThank you <a href=\"https://www.kaggle.com/aman2000jaiswal\" target=\"_blank\">@aman2000jaiswal</a>, <a href=\"https://www.kaggle.com/furcifer\" target=\"_blank\">@furcifer</a> !!</p>\n<p>But I am still confusing about how to calculate Confidence.<br>\n𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)<br>\nWhy did this formula use \"Percent\" for calculating Confidence?</p>",
      "rawMarkdown": "Thank you your comment.\nI come to know this \"Confidence\" is equal to statistical definition.\nThank you @aman2000jaiswal, @furcifer !!\n\n\nBut I am still confusing about how to calculate Confidence.\n𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)\nWhy did this formula use \"Percent\" for calculating Confidence?",
      "votes": null
    },
    {
      "id": "1007275",
      "postDate": "09/12/2020 03:01:24",
      "content": "<p>Any statistical estimate can be used inplace of percent. Estimate means mean, median etc.<br>\nI am talking about this in general.<br>\nwith respect to your above reply Estimate is patient's FVC as a percent</p>",
      "rawMarkdown": "Any statistical estimate can be used inplace of percent. Estimate means mean, median etc.\nI am talking about this in general.\nwith respect to your above reply Estimate is patient's FVC as a percent",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1002381,
      "author_name": "aman2000jaiswal",
      "author_url": "",
      "post_date": "09/08/2020 05:04:57",
      "content": "<h4>In brief</h4>\n<p>Confidence interval shows whether our assumed hypothesis fall in between or not.<br>\nand percentage is the probability which shows what is the probability of getting assumed hypothesis to be true.</p>\n<h5>for more <a href=\"https://www.bmj.com/about-bmj/resources-readers/publications/statistics-square-one/4-statements-probability-and-confiden\" target=\"_blank\">check this</a></h5>",
      "votes": null,
      "replies": [
        {
          "id": 1003384,
          "author_name": "tea0925ds",
          "author_url": "",
          "post_date": "09/08/2020 22:37:39",
          "content": "<p>Thank you your comment.<br>\nYeah, I know confidence interval and percentage in statistics.<br>\nBut in this competition, “Percent” means this.</p>\n<p>“a computed field which approximates the patient's FVC as a percent of the typical FVC for a person of similar characteristics”</p>\n<p>I didn’t understand why we can calculate “Confidence” from this “Percent”.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1003426,
          "author_name": "furcifer",
          "author_url": "",
          "post_date": "09/09/2020 00:51:05",
          "content": "<p>Are you assuming the confidence in the competition is referring to something else? So far my assumption is this is nothing different. </p>\n<p>\"Confidence levels are expressed as a percentage (for example, a 95% confidence level). It means that should you repeat an experiment or survey over and over again, 95 percent of the time your results will match the results you get from a population (in other words, your statistics would be sound!). Confidence intervals are your results and they are usually numbers. For example, here, for a specific group of features, we want to know FVC. You test your statistics at the 99 percent confidence level and get a confidence interval of (x,y). That means you think the FVC is between x and y You’re super confident (99% is a very high level!) that your results are sound, statistically.\" Correct me if I'm wrong.</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1007230,
          "author_name": "tea0925ds",
          "author_url": "",
          "post_date": "09/12/2020 00:38:34",
          "content": "<p>Thank you your comment.<br>\nI come to know this \"Confidence\" is equal to statistical definition.<br>\nThank you <a href=\"https://www.kaggle.com/aman2000jaiswal\" target=\"_blank\">@aman2000jaiswal</a>, <a href=\"https://www.kaggle.com/furcifer\" target=\"_blank\">@furcifer</a> !!</p>\n<p>But I am still confusing about how to calculate Confidence.<br>\n𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)<br>\nWhy did this formula use \"Percent\" for calculating Confidence?</p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 1007275,
          "author_name": "aman2000jaiswal",
          "author_url": "",
          "post_date": "09/12/2020 03:01:24",
          "content": "<p>Any statistical estimate can be used inplace of percent. Estimate means mean, median etc.<br>\nI am talking about this in general.<br>\nwith respect to your above reply Estimate is patient's FVC as a percent</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1002218": "I sometime saw the formula like this.\n\n𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)\n\nI couldn't understand the relation between Confidence and Percent.\nCould someone explain that?\nThank you for looking this discussion.",
    "1002381": "#### In brief\nConfidence interval shows whether our assumed hypothesis fall in between or not.\nand percentage is the probability which shows what is the probability of getting assumed hypothesis to be true.\n##### for more [check this](https://www.bmj.com/about-bmj/resources-readers/publications/statistics-square-one/4-statements-probability-and-confiden)",
    "1003384": "Thank you your comment.\nYeah, I know confidence interval and percentage in statistics.\nBut in this competition, “Percent” means this.\n\n“a computed field which approximates the patient's FVC as a percent of the typical FVC for a person of similar characteristics”\n\nI didn’t understand why we can calculate “Confidence” from this “Percent”.",
    "1003426": "Are you assuming the confidence in the competition is referring to something else? So far my assumption is this is nothing different. \n\n\"Confidence levels are expressed as a percentage (for example, a 95% confidence level). It means that should you repeat an experiment or survey over and over again, 95 percent of the time your results will match the results you get from a population (in other words, your statistics would be sound!). Confidence intervals are your results and they are usually numbers. For example, here, for a specific group of features, we want to know FVC. You test your statistics at the 99 percent confidence level and get a confidence interval of (x,y). That means you think the FVC is between x and y You’re super confident (99% is a very high level!) that your results are sound, statistically.\" Correct me if I'm wrong.",
    "1007230": "Thank you your comment.\nI come to know this \"Confidence\" is equal to statistical definition.\nThank you @aman2000jaiswal, @furcifer !!\n\n\nBut I am still confusing about how to calculate Confidence.\n𝐶𝑜𝑛𝑓𝑖𝑑𝑒𝑛𝑐𝑒=𝑃𝑒𝑟𝑐𝑒𝑛𝑡+𝑎.𝑞𝑢𝑎𝑛𝑡𝑖𝑙𝑒(0.75)∗𝑎𝑏𝑠(𝑤𝑒𝑒𝑘−𝑤𝑒𝑒𝑘𝑡𝑒𝑠𝑡)\nWhy did this formula use \"Percent\" for calculating Confidence?",
    "1007275": "Any statistical estimate can be used inplace of percent. Estimate means mean, median etc.\nI am talking about this in general.\nwith respect to your above reply Estimate is patient's FVC as a percent"
  },
  "source": "meta"
}