+ Reply to Thread
Page 2 of 2 FirstFirst 1 2
Results 16 to 28 of 28

Thread: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

  1. #16
    Points: 384, Level: 7
    Level completed: 68%, Points required for next Level: 16

    Posts
    11
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!




    REPOSTED FROM ANOTHER PRIVATE BOARD WHERE THIS DISCUSSION ORIGINATED:

    The statistics website that says time is a factor..... point out these simple points

    Anderson County has no significant demographic shift.... all polls open and close at the same time and these are numbers base off of total votes for the day...... so even if [a specific candidates] people all vote at exactly 8:25 AM it woudnt show up at all cause these numbers are tallied at 7 pm.
    []
    Time has no affect whatsoever cause no numbers were released by time.... no numbers were released seperate of the total vote over a period of time that went from poll opened to poll closed. If they were looking at exit polls not matching its a legit beef cause they were done early in the day. But we are looking at final precinct numbers only
    presence

  2. #17
    Points: 384, Level: 7
    Level completed: 68%, Points required for next Level: 16

    Posts
    11
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Ok... I was a bit confused in the type of this data set.

    Also from that board:

    they are total percent of the over all vote by precinct size

    so (made up numbers here( 5,000 or less precincts make up the first 10%... 5-10,000 make up 10-30%..... 10,000+ make up 30% to 100% this is where the numbers start showing through.... cause the lower precincts show a flip once you hit a certain vote size precinct EVEN IN DEMOGRAPHICALLY NEUTRAL counties
    I'm working with this individual to send raw data.

    thanks5
    03

    0
    .1320320202+
    02
    2102214.005+5300

    (my toddler is helping)

    presence

  3. #18
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Voting usually comes in first in the US (or are counted first) in rural counties than urban ones. This is why voting results commonly shift signficantly over time (democrats commonly do better as more votes come in than in the beginning because commonly they do better with the voters who get counted last - those in urban areas).
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  4. #19
    Ninja say what!?!
    Points: 8,297, Level: 61
    Level completed: 49%, Points required for next Level: 153
    Link's Avatar
    Posts
    1,165
    Thanks
    37
    Thanked 84 Times in 76 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    It appears one of the main issues you're dealing with is the assumption of randomness.

    If all the votes were counted COMPLETELY randomly, then what you saw in the graphs would be extremely odd and worth looking into. However, votes are normally counted by counties. In addition, each county does not have equal weight (i.e. Story County or others might have populations much larger than Sioux County). So hypothetically, all the votes from counties supporting Santorum and Paul might have been counted and reported first and votes from counties supporting Romney might have been counted later.

    The concepts you've looked up in regards to CIs only apply when the sample taken is not biased. If we accept that earlier counts were biased towards Santorum and Paul, the CI's would be meaningless.


    Edit: Dang. Noetsi got to it first. I gotta start responding sooner, rather than opening numerous threads and replying later!

  5. #20
    TS Contributor
    Points: 22,344, Level: 92
    Level completed: 99%, Points required for next Level: 6
    spunky's Avatar
    Location
    vancouver, canada
    Posts
    2,135
    Thanks
    166
    Thanked 537 Times in 431 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Quote Originally Posted by presence View Post
    Given that we expect there are standard/normal tallying procedures


    this is where you're really going to need to sink your teeth deep into in order to show what you'd like to show, starting for acknowledging the fact that there is no such thing as a "normal/standard tallying procedure". there are different procedures that are used for different things and, at least from what i remember when i worked with the people from Statistics Canada (StatsCan), they're usually contained in long, tedious and complicated manuals.





    Quote Originally Posted by presence View Post
    You seem to be avoiding the meat and potatoes I would expect from a number crunching statistician
    we're not avoiding the argument, but one thing we all are here are pretty rigorous scientists. in the spirit of good science (i.e. presenting alternative theories that could potentially explain the same data results in a more parsimonious way), we're offering a highly plausible theory that makes sense of the graphs you are looking at and challenge the theory you've came up with (an irregularity in the election VS methodology artifact). now, with that being said i am not implying i am 100% sure the election was not rigged in a certain way. maybe it was, maybe it wasn't. but one thing i am sure of is that neither the graphs nor the raw data by themselves will be enough to present formal evidence to show an irregularity in the election.
    for all your psychometric needs! https://psychometroscar.wordpress.com/about/

  6. The Following 5 Users Say Thank You to spunky For This Useful Post:

    Dason (02-22-2012), Jake (02-22-2012), ledzep (02-22-2012), Link (02-22-2012), SiBorg (02-22-2012)

  7. #21
    Fortran must die
    Points: 58,790, Level: 100
    Level completed: 0%, Points required for next Level: 0
    noetsi's Avatar
    Posts
    6,532
    Thanks
    692
    Thanked 915 Times in 874 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Quote Originally Posted by Link View Post
    It appears one of the main issues you're dealing with is the assumption of randomness.

    If all the votes were counted COMPLETELY randomly, then what you saw in the graphs would be extremely odd and worth looking into. However, votes are normally counted by counties. In addition, each county does not have equal weight (i.e. Story County or others might have populations much larger than Sioux County). So hypothetically, all the votes from counties supporting Santorum and Paul might have been counted and reported first and votes from counties supporting Romney might have been counted later.

    The concepts you've looked up in regards to CIs only apply when the sample taken is not biased. If we accept that earlier counts were biased towards Santorum and Paul, the CI's would be meaningless.


    Edit: Dang. Noetsi got to it first. I gotta start responding sooner, rather than opening numerous threads and replying later!
    You answer sound a lot better to me

    The best way to know if the data is likely rigged would be to compare voting behavior and turnout with past elections. Irregularities in turnout or the type of canidate who was voted for (although both subjective in nature) that was extreme might suggest a problem. That is the way such analysis is done I think.
    "Very few theories have been abandoned because they were found to be invalid on the basis of empirical evidence...." Spanos, 1995

  8. #22
    TS Contributor
    Points: 18,889, Level: 87
    Level completed: 8%, Points required for next Level: 461
    CowboyBear's Avatar
    Location
    New Zealand
    Posts
    2,062
    Thanks
    121
    Thanked 427 Times in 328 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Quote Originally Posted by presence View Post
    REPOSTED FROM ANOTHER PRIVATE BOARD WHERE THIS DISCUSSION ORIGINATED:
    Anderson County has no significant demographic shift.... all polls open and close at the same time and these are numbers base off of total votes for the day...... so even if [a specific candidates] people all vote at exactly 8:25 AM it woudnt show up at all cause these numbers are tallied at 7 pm.
    []
    Time has no affect whatsoever cause no numbers were released by time.... no numbers were released seperate of the total vote over a period of time that went from poll opened to poll closed. If they were looking at exit polls not matching its a legit beef cause they were done early in the day. But we are looking at final precinct numbers only
    I really don't follow the logic here. Clearly, some votes are counted first, and then others. The order that the votes are counted in, as we keep repeating, is not random. Most likely the order the votes are counted in depends on where they sit in the ballot boxes (influenced by time), and which polling stations count quicker (depending on geographical location). These effects will result in different candidates showing different trajectories in the graph. The non-randomness of the counting order also means that this stuff about dice rolls is irrelevant, and that we can't just give you a formula to easily check whether the results are reasonable.

    Quote Originally Posted by presence View Post
    I was kinda hoping this board would be able to provide me with more concrete statistical assumptions than armchair phrases like "we might expect something like this to happen". That statement is the armchair skeptic stuff you get in a 911 truther forum. I think; I know we can do better.
    You're complaining about armchair skepticism while refusing to follow simple and easy-to-follow suggestions for actually evaluating the claims you're making. I.e.
    You're claiming that you're seeing an irregular and fraudulent pattern in this particular election, while making no effort to see whether similar patterns hold in other elections. I would suggest that you go and do that.

  9. The Following 4 Users Say Thank You to CowboyBear For This Useful Post:

    Dason (02-22-2012), ledzep (02-22-2012), Link (02-22-2012), spunky (02-22-2012)

  10. #23
    TS Contributor
    Points: 22,344, Level: 92
    Level completed: 99%, Points required for next Level: 6
    spunky's Avatar
    Location
    vancouver, canada
    Posts
    2,135
    Thanks
    166
    Thanked 537 Times in 431 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    click on 2:12 to summarize my thoughts after reading other people's responses... this part is from the movie: "The Messenger: The Story of Joan of Arc"


    ps- i am like SO glad i finally get to use the youtube tags for something that's actually meaningful...

    for all your psychometric needs! https://psychometroscar.wordpress.com/about/

  11. The Following 6 Users Say Thank You to spunky For This Useful Post:

    CowboyBear (02-22-2012), Eyecatcher (10-11-2012), jpkelley (02-22-2012), Link (02-22-2012), TheEcologist (10-08-2012), trinker (02-22-2012)

  12. #24
    Probably A Mammal
    Points: 31,087, Level: 100
    Level completed: 0%, Points required for next Level: 0
    bryangoodrich's Avatar
    Location
    Sacramento, California, United States
    Posts
    2,564
    Thanks
    398
    Thanked 618 Times in 551 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    That clip from that point on is probably one of the best explanations for so many things I've ever seen! hahaha

  13. #25
    RoboStataRaptor
    Points: 11,861, Level: 71
    Level completed: 53%, Points required for next Level: 189
    bukharin's Avatar
    Location
    Sydney, Australia
    Posts
    1,312
    Thanks
    12
    Thanked 326 Times in 315 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Confirmation bias a la Hollywood... love it!

  14. #26
    Points: 384, Level: 7
    Level completed: 68%, Points required for next Level: 16

    Posts
    11
    Thanks
    3
    Thanked 0 Times in 0 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Ok... I just want to say thank you to the forum for hearing me out. I need to state that my inclination on this subject has shifted drastically as I have been informed that the X scale on the graph IS NOT relative to "percent of total votes in" but rather is "percentile of relative caucus size".

    This changes my hypothesis and my general "wave red flags" attitude towards the whole issue. I do think there may be something to explain... but in no way am I as concerned as I was before.

    Thank you again... sorry for wasting your time on false pretenses. If possible, I am going to go back and update the OP to direct to this comment.

  15. #27
    R purist
    Points: 35,103, Level: 100
    Level completed: 0%, Points required for next Level: 0
    TheEcologist's Avatar
    Location
    United States
    Posts
    1,921
    Thanks
    303
    Thanked 607 Times in 341 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!

    Quote Originally Posted by spunky View Post
    click on 2:12 to summarize my thoughts after reading other people's responses... this part is from the movie: "The Messenger: The Story of Joan of Arc"


    ps- i am like SO glad i finally get to use the youtube tags for something that's actually meaningful...

    Wow thanks for posting this, it's great.
    The true ideals of great philosophies always seem to get lost somewhere along the road..

  16. #28
    Points: 10,858, Level: 69
    Level completed: 2%, Points required for next Level: 392

    Posts
    360
    Thanks
    24
    Thanked 19 Times in 18 Posts

    Re: Vote Fraud in Iowa??? Tell me how this is statistically possible please!


    Couldn't it just be based on the order in which counties report their vote totals? Maybe Romney won larger cities which could take longer to count and tally. Thus, candidates who did well in smaller, rural areas may see large % early in the night but as the larger cities report their totals the urban candidates will start to fair better?

+ Reply to Thread
Page 2 of 2 FirstFirst 1 2

           




Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats