• 25 Posts
  • 521 Comments
Joined 1 year ago
cake
Cake day: July 9th, 2023

help-circle

  • God.fucking.dammit.

    When these two debates were announced, I knew it was going to be fucked up, but NO. Oooh he’s got to debate! He’ll show everyone how bad trump is! He needs to do it to help the undecideds!

    Fucking insane gibberish of a person who learned NOTHING from 2016. We got away with it in 2020 on the sheer novelty of an adult, a representative of government, telling trump to shut the fuck up. Now that was good tv. But it was a one-off.

    And now look at this shit. These fuckheads who can’t wait to elect trump are all up in here going “ooooh noooo Biden’s so bad he’s making us have trump be elected!1!!”

    Goddammit. The fucking “Operation gENoSiDE jOe” wasn’t gaining enough traction so THANK FUCK a bunch of Harvard MBA fuckups roundly decided Joe should stand on stage with a demented socopathic rapist who is functionally incapable of telling the truth and, y’know, give folks in the rural areas a little of the ol’, y’know, compare and contrast! What a goddamned brilliant idea. Hey! Let’s do it twice! Yeah! We are soooo smrt.

    Son of a fucking bitch, now we have to watch this garbage-truck-off-a-cliff-in-slow-motion for probably the next three months while all the Li’l Che Guevaras pile in every thread like clowns in a decrepit, backfiring bus, farting and defecating the same pointless key phrases over and over.

    DNC, you fucked up again because you refuse to understand how media works. Trumps out here kicking in windows and laughing and you guys are faxing press releases to republiQan-run news organizations and hoping their spin isn’t terrible. Christ in a bucket.


  • From your link:

    In practice, the sample size used in a study is usually determined based on the cost, time, or convenience of collecting the data, and the need for it to offer sufficient statistical power.

    You see how the elements listed there (cost, time, convenience, and ‘sufficient statistical power’) are more qualitative measurements and not known constants? (I mean, whenever it starts with, “In practice . . .” you know it means “in a perfect system devoid of unknowns”, or in other words “ideally but you’ll see it doesn’t work exactly like that” )

    What is the sufficient statistical power for sampling Europe? 0.002%? Two thousandths of a single percent? That greenlights your findings? Okay. I disagree. Polling companies don’t disagree because in this case, as you noted, 20k is an amazing sample size. The cost and time for that - not to mention the convenience! - alone is amazing . . for an opinion poll. No doubt they’re proud, that’s a fine achievement for an opinion poll. Now: did they measure what they set out to measure? I doubt it, but since the methodology given is the single word “online”, I remain skeptical.

    And saying “but there’s math in it!” is exactly why I’m skeptical. That effectively means nothing, and it’s used to validate whatever conclusions were presented. “We ran the numbers, and . . ” can mean very specific things, and in some contexts it is good enough to move on to the conclusions. Polls trade on that, but they don’t deserve to.

















  • Okay here’s the Methodology section:

    Methodology

    This report is based on a public opinion poll of adult populations (aged 18 and over) conducted in May 2024 in 15 countries (Bulgaria, the Czech Republic, Estonia, France, Germany, Great Britain, Greece, Italy, Poland, Portugal, the Netherlands, Spain, Sweden, Switzerland, and Ukraine). The total number of respondents was 19,566.

    The poll was conducted online by Datapraxis and YouGov in the Czech Republic (9-16 May, 1,071 respondents), France (9-20 May, 1,502), Germany (9-17 May, 2,026), Great Britain (9-13 May, 2,082), Greece (1-16 May, 1,093), Italy (9-17 May, 1,036), Poland (9-23 May, 1,550), Portugal (9-20 May, 1,070), the Netherlands (9-15 May, 1,014), Spain (9-17 May, 1,508), Sweden (9-23 May, 1,026), and Switzerland (2-15 May, 1,079). It was conducted online by Datapraxis and Alpha Research in Bulgaria (9-23 May, 1,000), and online by Datapraxis and Norstat in Estonia (6-21 May, 1,009). In all these countries the sample was nationally representative of basic demographics and past votes.

    In Ukraine, the poll was conducted by Datapraxis and Rating Group (7-12 May, 1,500) via telephone interviews (CATI) with respondents selected using randomly generated telephone numbers. The data was then weighted to basic demographics. Fully accounting for the population changes due to the war is difficult, but adjustments have been made to account for the territory under Russian occupation. This, combined with the probability-based sampling approach, strengthens the level of representativeness of the survey and generally reflects the attitudes of Ukrainian public opinion in wartime conditions.

    Some of the questions were not asked in Great Britain and Switzerland. The questionnaire in Ukraine included several questions that were not asked elsewhere. Overall, the graphs in this paper display data for all the countries in which the respective question was asked.

    Which - says who did it, but except for “online” or in the case of Ukraine “random telephone numbers”, it doesn’t describe the Method of the . . y’know, the Ology. So. “online”. Like, click on an Ad at stormfront.com, or -?

    Anyway here’s the numbers: