<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<div><br></div><div><br></div><div><br></div><div>Jan 24, 2021, 22:20 by allan.mustard@osmfoundation.org:<br></div><blockquote class="tutanota_quote" style="border-left: 1px solid #93A3B8; padding-left: 10px; margin-left: 5px;"><p><span class="font" style="font-family:Helvetica, Arial, sans-serif">Niels, et al,</span><br></p><p><span class="font" style="font-family:Helvetica, Arial, sans-serif">The Central Limit
Theorem does not predict that answers to a questionnaire will
follow a normal distribution. Rather,</span><br></p><p><span class="font" style="font-family:Helvetica, Arial, sans-serif">> when independent
random variables are added</span><br></p></blockquote><div>The problem is that this assumption does not hold at all. Variables (people answering)<br></div><div>are not independent at all.<br></div><div><br></div><div>Someone spreading info about survey in their mapping community will cause<br></div><div>sort-of-similar people to answer, especially if given group is focused on some <br></div><div>topic or characteristic.<br></div><div><br></div><div>Effect is greater for people efficient at convincing their community to answer survey.<br></div><div><br></div><div>----------<br></div><div><br></div><div>Also, variables are not random. For example, lying or answering strategically<br></div><div>is clear case of non-random distribution that will increase error.<br></div><div><br></div><div><br></div><div>=================<br></div><div><br></div><div>Survey will likely be useful, but error will be much greater than it would be in cases<br></div><div>where answers could be assumed to be <span style="" class=""><span class="font" style="font-family:Helvetica, Arial, sans-serif">independent
random variables.</span></span><br></div><blockquote class="tutanota_quote" style="border-left: 1px solid #93A3B8; padding-left: 10px; margin-left: 5px;"><p><span class="font" style="font-family:Helvetica, Arial, sans-serif">In an ideal world we
would a) identify all members of the OSM global community and b)
conduct a census of them. This is impossible. </span><br></p></blockquote><div>I agree.<br></div><blockquote class="tutanota_quote" style="border-left: 1px solid #93A3B8; padding-left: 10px; margin-left: 5px;"><div><span class="font" style="font-family:Helvetica, Arial, sans-serif">We thus conduct
a survey, make it as large as possible, and advertise it widely
so as to reach as many corners of the OSM community as
possible. We have translated it into 15 languages from the
original English. We are promoting it through all manner of
communications channels. If we are missing something, please
suggest how to address it. </span><br></div></blockquote><div>Spam PMs/changeset comments to active mappers? May be to aggressive.<br></div><div><br></div><div>I would go through <a href="https://wiki.openstreetmap.org/wiki/Automated_Edits_code_of_conduct">https://wiki.openstreetmap.org/wiki/Automated_Edits_code_of_conduct</a><br></div><div>process before doing this.<br></div><div><br></div> </body>
</html>