<div dir="ltr"><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small">Muito bom, Neale!</div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small"><br></div><b>“Probability samples are based on everyone’s having a known chance of being included in the sample. And we never know this probability”.</b><div><br></div><div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small">Quanta discussão cabe aqui.</div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small"><br></div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small">Abraço,</div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small"><br></div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small">André Maia.</div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small"><br></div><div class="gmail_default" style="font-family:verdana,sans-serif;font-size:small"><br></div></div></div><div class="gmail_extra"><br><div class="gmail_quote">2015-09-01 9:59 GMT-03:00 Neale El-Dash <span dir="ltr"><<a href="mailto:neale.eldash@gmail.com" target="_blank">neale.eldash@gmail.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Segue um artigo do Gelman publicado no Washington Post sobre pesquisas eleitorais. O comeco do artigo discute alguns detalhes metodologicos sobre pesquisas telefonicas/online feitas nos EUA. Mas o final vale pra qualquer lugar, qualquer metodologia. Segue um paragrafo que eu gosto bastante, e resume tambem minha opiniao sobre o assunto:<div><br></div><div><p class="MsoNormal"><span lang="EN-US" style="font-family:Arial,sans-serif;background-image:initial;background-repeat:initial">"</span><span lang="EN-US" style="font-size:13.5pt;line-height:115%;font-family:Georgia,serif;color:rgb(17,17,17);background-image:initial;background-repeat:initial">In
real life there are no probability samples of humans. With survey response
rates below 10 percent, there is no way to know the probability of an
individual being included in the sample. You can know the probability that the
survey organization will <em><span style="font-family:Georgia,serif">try</span></em> to
reach a person — that’s easy, it just depends on exactly how the address or
telephone number or e-mail is sampled from a given list. But it’s impossible to
know the probability that this person will actually be included in the sample,
as this depends on the probability that the person is reached, multiplied by
the probability that he or she agrees to respond, given that he or she is
reached. <span style="font-size:13.5pt;line-height:115%;font-family:Georgia,serif;background-image:initial;background-repeat:initial">And neither of these two
probabilities is ever known</span></span><span style="font-family:Arial,sans-serif;background-image:initial;background-repeat:initial">"</span></p></div><div><div><br></div><div>Link para o artigo:</div><div><a href="http://www.washingtonpost.com/blogs/monkey-cage/wp/2015/08/31/heres-why-you-should-worry-about-the-polls-for-the-2016-u-s-elections-and-beyond/" target="_blank">http://www.washingtonpost.com/blogs/monkey-cage/wp/2015/08/31/heres-why-you-should-worry-about-the-polls-for-the-2016-u-s-elections-and-beyond/</a><span class="HOEnZb"><font color="#888888"><br clear="all"><div><br></div>-- <br><div><div dir="ltr"><div><div dir="ltr"><div><br></div>Knowledge is only part of understanding. Genuine understanding comes from hands-on experience.</div><div dir="ltr">(Seymour Papert)<br><div><br>-----------------------------------------------<br>Neale Ahmed El-Dash<br>Doutor em Estatística<br>Celular: <a href="tel:%2B55%2019%20998893939" value="+5519998893939" target="_blank">+55 19 998893939</a><br>Email: <a href="mailto:neale.eldash@gmail.com" target="_blank">neale.eldash@gmail.com</a><div style="display:inline"></div></div></div></div></div></div>
</font></span></div></div></div>
<br>_______________________________________________<br>
abe mailing list<br>
<a href="mailto:abe@lists.ime.usp.br">abe@lists.ime.usp.br</a><br>
<a href="https://lists.ime.usp.br/mailman/listinfo/abe" rel="noreferrer" target="_blank">https://lists.ime.usp.br/mailman/listinfo/abe</a><br>
<br></blockquote></div><br></div>