Posted on 11/05/2020 11:21:16 AM PST by karpov
I am making these tweets to explain in one place some analysis that was done last night. 1 - I was asked offline about doing Benford's on election data. I explained that this is common and a useful way to detect anomalies in data that are driven by artificial process (e.g. fraud)
2 - My student then pointed me towards a tweet that was exploring this type of analysis (but they hadn't done Benford's). So I chimed in.
3 - However, I did not know what data they used so I found a source for the context they referenced. However, I could not initially find write-ins versus non-write-ins, so I looked at candidate counts.
4 - I then wrote a quick script to gather that data, here is an example of what the data gathering portion of this process looked like.
6 - I wrote the code to produce the Benford's discrete distribution. This code looks like this.
7 - Now that I had the data and the distribution, I simply needed to perform the test. To do that, I leveraged scipy's chisquare. However, prior to doing that, you need to produce the expected result values (not just the percentages. But this is as simple.
8 - To do that, you take the total number of observations (number of numbers that the first digit counts are derived from) and multiply them by the Benford's distribution frequencies accordingly. This looks like this:
(Excerpt) Read more at twitter.com ...
The Python code is here. Maybe some Freepers can replicate the analysis.
Chisquare is the boss.
I haven't taken statistics in a long time, but I sure remember that statistic basically telling you if a new set of data is for all intent, bogus, given a known set of data.
Could someone translate this thread in simple envy?
Excellent!
Math doesn’t lie!
To all you criminals, including those on this site, you’re done for!
English please
Not a statistician but I have been wondering if there has been an analysis of precincts that tend more towards conservative down-ballot candidates or propositions, but then skew heavily to Biden over Trump, that would seem to be a contradiction and might indicate fraud at the top of the ballot.
When the occurrence of events is random, the associated patterns are very different from patterns associated with events that are coordinated in a deliberate and planned manner.
The fraudulent delivery of ballots leaves an identifiable pattern.
https://www.law.cornell.edu/uscode/text/52/20511
52 U.S. Code 20511.Criminal penalties
A person, including an election official, who in any election for Federal office—
(1) knowingly and willfully intimidates, threatens, or coerces, or attempts to intimidate, threaten, or coerce, any person for—
(A) registering to vote, or voting, or attempting to register or vote;
(B) urging or aiding any person to register to vote, to vote, or to attempt to register or vote; or
(C) exercising any right under this chapter; or
(2) knowingly and willfully deprives, defrauds, or attempts to deprive or defraud the residents of a State of a fair and impartially conducted election process, by—
(A) the procurement or submission of voter registration
applications that are known by the person to be materially false, fictitious, or fraudulent under the laws of the State in which the election is held; or
(B) the procurement, casting, or tabulation of ballots that are known by the person to be materially false, fictitious, or fraudulent under the laws of the State in which the election is held,
shall be fined in accordance with title 18 (which fines shall be paid into the general fund of the Treasury, miscellaneous receipts (pursuant to section 3302 of title 31), notwithstanding any other law), or imprisoned not more than 5 years, or both.
https://www.law.cornell.edu/uscode/text/52/20511
52 U.S. Code 20511.Criminal penalties
A person, including an election official, who in any election for Federal office—
(1) knowingly and willfully intimidates, threatens, or coerces, or attempts to intimidate, threaten, or coerce, any person for—
(A) registering to vote, or voting, or attempting to register or vote;
(B) urging or aiding any person to register to vote, to vote, or to attempt to register or vote; or
(C) exercising any right under this chapter; or
(2) knowingly and willfully deprives, defrauds, or attempts to deprive or defraud the residents of a State of a fair and impartially conducted election process, by—
(A) the procurement or submission of voter registration
applications that are known by the person to be materially false, fictitious, or fraudulent under the laws of the State in which the election is held; or
(B) the procurement, casting, or tabulation of ballots that are known by the person to be materially false, fictitious, or fraudulent under the laws of the State in which the election is held,
shall be fined in accordance with title 18 (which fines shall be paid into the general fund of the Treasury, miscellaneous receipts (pursuant to section 3302 of title 31), notwithstanding any other law), or imprisoned not more than 5 years, or both.
The problem is that most (all?) judges do not understand math nor statistics.
They would understand if they went into a casino and rolled 10 consecutive seven’s at the craps table.
They understand a generalized summation of it, as in post #7. All judges can understand it, every last one of them.
http://freerepublic.com/focus/bloggers/3902254/posts?page=7#7
LOL!!!
Interesting zero hedge article here:
Data-driven ping
The evidence mounts....and that is a huge chunk.
Just no way that can happen apart from rigging.
There should be very few differences in the voting patterns of Ohio, with that of Michigan, Wisconsin and Pennsylvania.
As much as I hate DeNiro, Trump is DeNiro, and the guy that gets his hand smashed are the Dem cheaters who have been caught.
A liberal friend of James Woods pointed that out.Glad to see it affirmed.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.