You are viewing an obsolete version of the DU website which is no longer supported by the Administrators. Visit The New DU.
Democratic Underground Latest Greatest Lobby Journals Search Options Help Login
Google

Reply #76: not 100% [View All]

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
This topic is archived.
Home » Discuss » Topic Forums » Election Reform Donate to DU
Febble Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-09-06 05:18 AM
Response to Reply #64
76. not 100%
you won't get 100% until the audit percentage is greater than the percentage of uncorrupted machines. Of course the odds of not finding a single corrupt machine with a 2% audit if there are 40% corrupt machines is very low, but it is not zero. And we are talking about thousands of jurisdictions.

I'm not knocking audits, just cautioning against thinking that some magic number will given you 100% confidence. It might be better to interpret your table as telling you how confident you can be that the percentage of corrupt machines is less than a given percentage. For example, if your table is right, you can probably interpret it to say tell you what level of confidence you can have that a given percentage of machines are uncorrupted if your 2% audit comes up clean. So, with a 2% audit, if you are happy with p<.05 (95% chance of being right), you can say that if your audit is clean, you can be statistically "confident" that no more than 15% of machines are corrupt. If you go down to p<.01 (99% chance of being right), you can merely say that you are confident that not more than 25% of your machines are uncorrupted. With many thousands of jurisdictions, I'd want my confidence to be at least 99% (1% chance of being wrong) that no more than, say 5% of machines were corrupted. That last percentage would, I suppose, depend on vote winning margin.

Looking at it a different way, if finding at least one corrupted machine triggers a full audit, then at least the 2% audit system will caution anyone trying to steal an election keep the percentage of corrupt precincts low. And also to do their best to make sure that the audit isn't random.

But I don't think 2% random audits are a panacea. I'd like someone to convince me.
Printer Friendly | Permalink |  | Top
 

Home » Discuss » Topic Forums » Election Reform Donate to DU

Powered by DCForum+ Version 1.1 Copyright 1997-2002 DCScripts.com
Software has been extensively modified by the DU administrators


Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.

Home  |  Discussion Forums  |  Journals |  Store  |  Donate

About DU  |  Contact Us  |  Privacy Policy

Got a message for Democratic Underground? Click here to send us a message.

© 2001 - 2011 Democratic Underground, LLC