<br><br><div class="gmail_quote">---------- Forwarded message ----------<br>From: <b class="gmail_sendername">Alexander Hapfelmeier</b> <span dir="ltr"><<a href="mailto:Alexander.Hapfelmeier@tum.de">Alexander.Hapfelmeier@tum.de</a>></span><br>
Date: 2009/2/19<br>Subject: ROC()<br>To: <a href="mailto:emmanuel.brasil@gmail.com">emmanuel.brasil@gmail.com</a><br><br><br>Hallo Sir,<br>
<br>
Today I searched some functionalities for ROC-Curves and found your function ROC(). It is a very good function to analyse ROC-Curves but its documentation brings up some questions. How are the CI computed? So I checked the code itself. CI are computed by Wilsons method. But there seems to be a problem with the CI auf the AUC. It is not the 95%-KI as you compute AUC +- SE(AUC). For me it is not clear if you did this by purpose or if it is a mistake.<br>
<br>
So I have two suggestions:<br>
- Maybe you could improve your documentation by including some specifications about the computational background e.g. mentioning that CI are computed by Wilsons method and so on...<br>
- A singificance level to the CI of the AUC should be added.<br>
<br>
Thank you very much for your efforts.<br>
Sincerely,<br>
<font color="#888888">Alexander Hapfelmeier<br>
</font></div><br><br clear="all"><br>-- <br>Abraço forte e que a força esteja com você,<br>Pedro Emmanuel<br>