Statistics

Stats I Did For the Sidney Powell Suits: 150 Thousand Missing Votes

Around 154 thousand votes or so (plus or minus) have perhaps gone missing across several states. In Pennsylvania alone maybe 30 thousand or so Republican ballots are not accounted for.

And that’s only the start of the story.

The whole story is long in detail, most of which we can skip today. There are many involved in all this, and my role is that of an army ant.

There are lots of people working on exposing the fraud, coming at it from all angles. I’ve talked and done things with several groups. Early on I suggested to Matt Braynard’s group (though it was a while before I talked to him) that surveys of a certain kind should be done in the disputed areas.

They wisely set aside my survey idea and instead did another, across several states. This article is only about Braynard’s survey. I’ll have more to say about other efforts later.

Haller (in the video above) contacted me, and I did an analysis of the Braynard survey. That analysis is contained in Sidney Powell’s (and others’) filing, one of which you can read here (there were multiple filings in different states; see her Twitter feed).

The idea is simple. In each of several states—Georgia, Michigan, Wisconsin, Arizona, and Pennsylvania—the state authorities recorded certain absentee ballots as missing, i.e. never returned. Obviously, the votes of these ballots categorized as missing were never counted.

Votes not counted are a no-no.

A professional poll called people on these lists (many thousands!) and asked two questions: (1) Did you request an absentee ballot? and, if so, (2) Did you return that ballot? (All these calls were recorded.)

There are obvious errors if (a) a person did not request an absentee ballot but got one, and (b) they returned the ballot but it was never recorded as received.

The total number of absentee ballots marked by authorities as never returned differed by states, but it was small nowhere: about one hundred thousand or more in each state; half a million in Arizona.

The survey itself was simplicity itself, asking short simple questions. It was merely a matter of extrapolating its numbers to the known population to produce the results, which are reproduced here.

Error #1: being recorded as sent an absentee ballot without requesting one.

Error #2: sending back an absentee ballot and having it recorded as not returned.

Here are the number of recorded unreturned ballots, and the 95% prediction bounds on those errors.

State Unreturned ballots Error #1 Error #2
Georgia 138,029 16,938–22,771 31,559–38,866
Michigan 139,190 29,611–36,529 27,928–34,710
Pennsylvania* 165,412 32,414–37,444 26,954–31,643
Wisconsin 96,771 16,316–19,273 13,991–16,757
Arizona 518,560 208,333–229,937 78,714–94,975

*Number for Pennsylvania represent Republican ballots only.

I emphasize: these are prediction bounds. For example, given the data and the model, there is a 95% chance from between 27 and 32 thousand Republican ballots went missing in Pennsylvania.

Ballots that were not requested, and ballots returned and marked as not returned were classed as troublesome. The estimated average number of troublesome ballots for each state were then calculated using the table above and are presented next.

State Unreturned ballots Troublesome Average Percent
Georgia 138,029 53,489 39%
Michigan 139,190 62,517 45%
Pennsylvania* 165,412 61,780 37%
Wisconsin 96,771 29,594 31%
Arizona 518,560 303,305 58%

*Number for Pennsylvania represent Republican ballots only.

Survey respondents were not asked if they received an unrequested ballot whether they sent these ballots back. This is clearly a lively possibility, and represents a third possible source of error, including the potential of voting twice (once by absentee and once at the polls). No estimates or likelihood can be calculated for this potential error due to absence of data.

Powell’s summary of some of these statistics:

In sum, with the expert analysis of William M. Briggs PhD based on recorded calls and declarations, the extent of missing AND unlawfully requested ballots create substantial evidence that the mail ballot system has fundamentally failed to provide a fair voting mechanism. In short, tens of thousands of votes did not count while the pattern of fraud makes clear that tens of thousands were improperly counted. This margin of victory in the election for Mr. Biden was only 12,670 and cannot withstand most of these criticisms individually and certainly not in aggregate.

Well, you get the idea. The law itself is as opaque to me as statistics are to others, but we don’t need to understand either to grasp that ballots marked as not returned, and therefore not recorded, are a major error if indeed, as people said, these ballots were returned.

This is especially so in Pennsylvania, where the survey was for Republicans only. Some 30 thousand or so of estimated missing Republican votes cannot be dismissed. An explanation is needed. For all five states.

That’s it for now. There’s much more to all this, including a tale of loathsome unethical irresponsible weaselly academics scuttling an earlier attempt at analyzing this data (not by me).

And, of course, there’s more to say about other analyses. We’ll leave all this for another day.

Happy Thanksgiving!

To support this site and its wholly independent host using credit card or PayPal (in any amount) click here

Categories: Statistics

57 replies »

  1. Let us not forget that the first Thanksgiving was a celebration of the first successful harvest after abandoning communism. The Pilgrims were literally thanking God for teaching them that harsh lesson.

  2. ‘models only say what we tell them to say’ and ‘probability cannot determine cause’…. except in this case when my model is good and it determines fraud happened. Right prof?

  3. Studanr,

    The problem of not studying hard enough is that you only remember half the lesson.

    And there is no good reason to keep changing your screen name, Justin. It’s pathetic.

  4. Were there similar questions asked of voters in states not disputed? Otherwise, how do we know all states were not like these five?

    I know people love math and math proof, but considering a reported 1000 people watched Joe’s Thanksgiving speech online while he got 80 million votes (more than any other person running for president–a Turnip in the Basement was the top vote getter of all time…..Sure…sure…..), virtually no one came to campaign rallies, votes were trucked in at 4 am, there are 47 missing data cards, more mail-in votes than ballots sent out, etc, any nation with an IQ above 70 would call that fraud. The simple fact that this is even questioned as not being fraud says the republic is OVER. Stupidity rules and we are toast. We don’t need math or a court to KNOW THIS IS TRUE.

    Have a nice Thanksgiving.

  5. “Stud”, I’m having difficulty finding your attribution in Briggs’ post. I read it as saying “[B]allots marked as not returned, and therefore not recorded, are a major error if indeed, as people said, these ballots were returned.”

    Briggs, did you do a NYT-style secret correction on us?
    😀

  6. Studanr may not have grasped the statistics of sampling, but he did learn Alinsky’s Rules for Radicals:
    RULE 5: “Ridicule is man’s most potent weapon.”

    Actually truth is the most potent weapon, but when radicals have no truth, ridicule works wonders with weak politicians. Note how often the press attacks a person (homophobic, racist, etc.) but never discusses their position on any issue.

  7. Dr Briggs to the rescue!

    Another thing to give thanks for: Thanks for being there at the right time, with the right skills and the right network to make a difference.

    Don’t ever give up.

  8. Go Briggs! Still a long difficult road to travel to give President Trump the victory he earned!

  9. Thanks Mr. Briggs. Good to know one of our boys making an appropriate contribution like this.

  10. I don’t see how the answer to the survey question about whether the ballot was returned is informative, since it does not ask when it was returned. We are free to assume that all of these ballots were returned after the deadline, and therefore should not have been counted.

    The court filing makes amusing reading. It’s an entertaining example of the elevation of models over data, as in the repeated assumption that the “failure” of certain votes to conform to a normal distribution is somehow evidence of shady business. But I don’t expect Briggs to criticise this statistical amateur-hour analysis in this case, since it supports the conclusions that he favors.

  11. Briggs, I’m picturing you storming enemy lines, machine gun spitting whole numbers, hurling equation grenades, and slashing away with a giant number 1 sword while the battlefield about you is littered with the shredded corpses of loathsome, unethical, irresponsible, and weaselly academics. Great movie, Sarge.

    “Don’t ever give up.” Great advice there, Kent. The main tactic of the enemy is media propaganda designed to deceive, demoralize, intimidate, panic, and frighten us into giving up. They make it look Great And Powerful but it’s just a phony magnifying trick put on by a cabal of miserable little Ozs puffed up on pride and plunder. Turn it off. There is still God’s great and wonderful world all about us, and God himself is all about us. There is literature and art and architecture and music aplenty in our heritage treasury from which to nourish the spirit. The best of our past can live in a man’s heart and mind now, helping to lift and carry us through this present challenge. Thanksgiving brings the many blessings we have at hand out of hiding and into our hearts. Eat and drink hearty, laddies, and let’s raise a toast to the provident host of this lively pub, the redoubtable, indubitable, statistical, mystical, and antihysteristical General William Matthew Briggs [clink!]

  12. Lee, Lee, Lee… — black pills washed down with kool-aid make a poor Thanksgiving meal. Here’s a glass of warm Thanksgiving cheer, sit there by the fire and warm your bones. Smell that? The pub keeper’s wife is an excellent cook, and the table will soon be groanin’ aplenty. I hope you’re hungry, ol’ boy.

  13. Dr Briggs, I cannot tell you how much I appreciate your comments and assessments. I have been watching what is going on for many years, now. It has been that long, you know. After all that watching, a phrase comes to mind that I believe is most pertinent, “Talks cheap, it takes money to buy whiskey”! I, truly, wish you a Happy Thanksgiving (even though you may be living in the “Communist State of MI” (my home state!

  14. It is kind of funny that Trump probably lost because of his on plan to sabotage USPS.

    Your analysis also ignores the amount of democrat who returned their ballot but the ballot were never received

    Though democrat advised voter to not send their ballot 8 to 10 days before the election. Something that Republicans tv never communicated to its viewer.

  15. The lawyer filing this lawsuit is the one recently denounced by the Trump legal team and scorned by Tucker Carlson—for adducing the very claims that are prominent in her filing, the one that Higgs—I mean Briggs—generated his “analysis” for.

    Statistician to the Stars, indeed!

  16. When I saw the name “William M. Briggs” in the report I thought, that William Briggs? The one whose blog I read? Is his middle initial “M” or is this someone else. Wait…a statistician? Must be him!

    So I came over to check and indeed it is he!

    I’m finding that more than a few players in this event are people I have been following online for years—and trust!

  17. Allow me to repost the Thanksgiving tradition here

    …………………………………………

    Then he commenced to pray to the Everywhere Spirit in the same stentorian voice, never sniveling but bold and free.

    “Thank you for making me a Human Being! Thank you for helping me become a warrior! Thank you for all my victories and for all my defeats. Thank you for my vision, and for the blindness in which I saw further.

    “I have killed many men and loved many women and eaten much meat. I have also been hungry, and I thank you for that and for the added sweetness that food has when you receive it after such a time.

    “You make all things and direct them in their ways, O Grandfather, and now you have decided that the Human Beings will soon have to walk a new road. Thank you for letting us win once before that happened. Even if my people must eventually pass from the face of the earth, they will live on in whatever men are fierce and strong. So that when women see a man who is proud and brave and vengeful, even if he has a white face, they will cry: ‘That is a Human Being!’…”

    I stood there in awe and Old Lodge Skins started to sing, and when the cloud arrived overhead, the rain started to patter across his uplifted face, mixing with the tears of joy there.

    It might have been ten minutes or an hour, and when it stopped and the sun’s setting rays cut through, he give his final thanks and last request.

    “Take care of my son here,” he says, “and see that he does not go crazy.”

    He laid down then on the damp rocks and died right away. I descended to the treeline, fetched back some poles, and built him a scaffold. Wrapped him in the red blanket and laid him thereon. Then after a while I started down the mountain in the fading light.

  18. The lawyer filing this lawsuit is the one recently denounced by the Trump legal team and scorned by Tucker Carlson

    Not denounced – distanced which could have been strategic.
    https://www.youtube.com/watch?v=1P1OiDjbsJM

    Tucker didn’t scorn her. You clearly don’t watch his program. He complained that she wouldn’t show him her evidence. Can’t blame her. Doing so would be like the cops sending the target of a search warrant advanced notice. Just invites destruction of evidence. Some of it already has been destroyed anyway. That alone should be prima facie evidence of fraud.

  19. It is kind of funny that Trump …

    Well, your saying it is funny.
    You might get a job as a stand-up comedian yet.
    Keep trying. Never give up.

  20. Mrs Powell could be representing other clients. Read somewhere that she is representing electors in GA (Georgia.). Should that not be part of the lawsuit itself?

  21. How striking that in critique more than one commenter said something like, “I expected this sort of biased twaddle from you, Briggs.” Almost as if the bulk of what Matt writes about hangs together — or doesn’t hang together — in a coherent way (or is incoherent in similar ways).

    I for one am just glad that Matt ‘integrated out’ the uncertainty in the parameters and thus, given the priors, could present a truly predictive estimate, just like I taught him. Well done, Sergeant, and a most blessed Thanksgiving to you and yours.

  22. As Winston Churchill once said about untruths, “there are lies, damn lies, and then statistics.” It is apt for the Affidavit which you executed in the Michigan lawsuit.

  23. Thank you Mr Briggs. I read the pdf last night and saw your name referenced in it. Time is ticking away – and that does not help any of these cases – there are so many things that do not add up in those 5 states – and probably more too.

    I for one am not surprised at what a mockery our election processes are – they have probably long been corrupted – because power corrupts. We may have noticed or suspected fraud – but as average folk we rarely really looked too deeply and then took real action on correcting the issues. It goes to a few quotes I have remembered over the years:

    “ If voting made any difference, they wouldn’t let us do it.” —Mark Twain

    “The people who cast the votes decide nothing. The people who count the votes decide everything.” —Joseph Stalin

    “The oppressed are allowed once every few years to decide which particular representatives of the oppressing class are to represent and repress them.” —Karl Marx

    The supposed social contract (don’t get me started) we all live under has been damaged beyond repair and what follows next is a whole series of unpredictable and unintended consequences.

  24. I really wish there was a control state, like FL in the analysis. They minimized the opportunity for motivated liberals — and that’s who works in these state agencies — to get up to no good; they counted the ballots as they came in. Seems like it would strengthen the case if FL’s rates were much lower.

  25. Briggs: I truly want to know why your are not looking at other states. You’re assumingthat where you got the desired resul (Trump winning) the “problems” you’re checking do not exist. You do not know that. Where’s the evidence that this is not widespread?

    JoeFL: Nope, ridicule definitely outranks truth as a weapon every time.

    Lee Phillips: Everything you disagree with is amateur hour. You’re a walking case of confirmation bias on steroids. However, you’re comments are informative as to how faith and confirmation bias can warp the planet, so the comments are welcome. Even the ad hominem you tossed in later. Always a bad example, but we need bad examples to know what good ones are.

    Sylvain, crazy as always. Gotta love that example, too.

    DAV: “Some of it already has been destroyed anyway. That alone should be prima facie evidence of fraud.” Nope, it’s how the Democrats roll, always have, and were never stopped. That would prima facie evidence that this is an acceptable practice after 50 plus years of use without complaints.

  26. Sander van der Wal- et al

    Powell is representing the electors in GA as well as Asst Cobb county GOP chairman, the lawsuit is on her site defendingtherepublic.org

    Mr. Briggs,

    Congratulations. Bravo.
    Now proving fraud and getting power are a different thing.

    Even if this succeeds it goes then to the House of Representatives.

    May I suggest when Biden is proclaimed the GOP walk out.
    It is about the only worthwhile, decent thing they can do.

  27. All I know is the fraud is real, my rage is white hot and I want to kill every last communist in the most barbaric midevil ways imaginable.

  28. NotVxxc : Even if this succeeds it goes then to the House of Representatives

    You haven’t been paying attention

    Each state only gets one vote.

    Each state’s House delegation as of Jan 3 would have one combined vote. If a majority of states go to one candidate, that candidate will be president. I believe the Republicans hold that key

  29. @spin gerahat,

    Then your first victim will be Trump. He is bigly friend with many communist leaders.

  30. There are only three leftist comments you will read when it comes to a prominent article:

    1.) “You’re wrong because of this prominent study that I am linking to (but didn’t bother to read and am unaware is irrelevant.)”

    2.) “You’re evil. Can you explain to us why you are so evil?”

    3.) “No U.”

  31. Every honest person who has looked at just a fraction of the evidence knows that funny business occurred on a grand scale. The problem is in what the courts are going to do with the evidence, given that judges are reluctant to order ballots tossed. Hopefully, this and other evidence will lead to a full bipartisan audit in the contested states.

  32. I have two questions:

    1) Can you name (identify) to us (readers of your post) the ‘professional poll’ entity?

    2) Is it possible for you to “show-your-work” for the Error#1 and Error#2 values?

  33. I can only speak for Pennsylvania and only anecdotally.
    First, I personally know of some Republican voters went to the polls on election day and were told that they requested a mail-in ballot and couldn’t vote normally but they would be able to cast a “provisional” ballot. Trump got 50,874 provisional votes, while Biden got 53,168.
    Second, a little over 10% of PA registered voters are “Non-Affiliated” or independent. They also requested about 10% of mail-in ballots and their return rate was below the state average.

  34. More on Pennsylvania

    I would like to see the raw voter registration data broken down by:
    People who voted in 2020 and voted in 2016.
    People who voted in 2020 but were registered and didn’t vote in 2016.
    People who voted in 2020 but weren’t registered in 2016.

    For these groups I would like to know:
    County
    Party of Registration in 2020
    Party of Registration in 2016
    Type of vote in 2020, i.e. Mail-in or Election Day

    And also to do a comparison with previous Presidential elections
    By County
    Number of people in each party who turned out to vote.
    Complete vote numbers (including write-ins), so it can be determined the number of ballots there were blank for each race.

    I would hope any competent campaign would already have nearly all this raw data on hand.

  35. Powell’s summary of your analysis appears to contradict your own.

    “””
    the extent of missing AND unlawfully requested ballots create substantial evidence that the mail ballot system has fundamentally failed to provide a fair voting mechanism
    “””

    However, you state Error 1 is people who received ballots without receiving them. Is there another part of your analysis you didn’t mention?

    Also, while I agree there needs what happened should be scrutinized, I would assume the majority of the uncounted votes one were for Biden, not Trump, since Biden voters were more likely to vote by mail

  36. “It is kind of funny that Trump probably lost because of his on plan to sabotage USPS.”

    You are correct. they got so efficient that PA sent out 1.8mm ballots but counted 2.5mm. Damn good job USPS! Damn good.

  37. How did the survey get the phone numbers of the voters who did not return their ballots? Last time I checked, voter records did not contain phone numbers.

    And where can we see the underlying data, the list of voters whose ballots were not returned, and their responses?

  38. The fact that only Republicans were called is just another source of unacceptable bias in the survey data. At a *bare* minimum, Democrats should have been called as well, and these numbers should have been compared.

    How did you control for calling the wrong number? How did you control for people with the same name? How did you control for people who were mistaken about whether they had requested a ballot?

    Without the answers to these and many other questions, the survey data is crap. And of course, with a statistical analysis, if you put crap in you get crap out.

  39. @Daniel M –
    Ever hear of a thing called a telephone directory?
    You see, it is possible to compare data in one database to data in another, and discover useful correlations.

Leave a Reply

Your email address will not be published. Required fields are marked *