Bad Stats

Back when I worked for the Great Big Research Company in Johannesburg, I had a boss who had the unnerving habit of doing random checks on my calculations.  (I should point out for my Readers who were born after we discovered the wheel that computations were done not with slide rules but with the newfangled invention called a “calculator” — which could do only the basic math functions of addition, subtraction, multiplication and division — and the literally thousands of numbers were taken off pages and pages of computer printouts from a thing called a “mainframe”.)

Anyway, if the Poison Dwarf (as we not-so-jokingly called him) discovered a single mistake, he would tear it all up and make me redo the entire job, with the rationale that “If I can’t trust one thing, I can’t trust anything.”  The result, after only a couple of these episodes, was that I not only took an inordinate amount of time in performing the calculations, but spent almost as much time rechecking everything to make sure that absolutely every statistic or number I presented to my clients was 100% correct, and they could take the actions I recommended with complete confidence in the strength of the data.

The time spent in doing all this was based on another of the Poison Dwarf’s aphorisms:  “There’s never enough time to do the job properly, but there always seems to be enough time to do things over.”  Well, I never had enough time to do things over — I had client meeting deadlines — so I had to get it right the first time, regardless of the time taken.

That habit persisted with me for the rest of my working career.

I say all this so everyone will know exactly where I stand on bullshit like this (with emphasis added):

A young Florida resident who died in a motorcycle accident is included in the state’s official COVID-19 death count, a state official reveals.
FOX 35 News in Orlando discovered this after asking Orange County Health Officer Dr. Raul Pino about two young COVID-19 patients in their twenties who died, and whether they had any preexisting conditions that contributed to their deaths.
“The first one didn’t have any. He died in a motorcycle accident,” Pino said. Despite this shocking answer, Pino was not aware of this person’s data being removed from the state tally when asked.
“I don’t think so. I have to double-check,” Pino answered. “We were arguing, discussing, or trying to argue with the state. Not because of the numbers — it’s 100… it doesn’t make any difference if it’s 99 — but the fact that the individual didn’t die from COVID-19… died in the crash.”

You stupid fucking quack.  It’s not whether it makes a difference between 99 and 100 — it’s how many more mistakes of this kind have occurred in your compilation of the data.

Remember the Poison Dwarf:  “If I can’t trust one thing, I can’t trust anything.” 

So if one death (1%, in this case) was incorrectly attributed to the Chinkvirus, how many more cases are incorrect?  10%?  20%?  90%?  We don’t know, because the numbers were obviously not checked after being submitted.

Here’s something from Powerline which makes the same case quite succinctly:

Funny, but not so funny.

Here’s the thing.  A lot of decisions, very weighty and momentous decisions, are being made based on the data our much-vaunted medical establishment is presenting.  States’ economies are being damaged or destroyed, people’s livelihoods ditto, and I’m not even going to start to estimate the social cost of foolish governmental decisions taken on the basis of what may turn out to be fatally-flawed data.

So I’m going to mimic the Poison Dwarf (for the first time ever):  I’m not going to trust a single fucking piece of data these assholes present to us, ever again.  As far as I’m concerned, it’s all lies and bullshit, and I don’t trust any of them.

24 comments

  1. Kim sed: “As far as I’m concerned, it’s all lies and bullshit, and I don’t trust any of them.”
    =========
    Right there.
    The primary law of life, now.
    There is SO much info out there and hardly anyone questions the validity of it.
    My default, now, is to never believe anything from the millions of anonymous “sources” and, instead rely on, with verification, of long term trusted sources.

  2. And don’t forget the comparisons. For example, assume testing shows 20% of the total population was tested “positive” for corona-chan. Well, what exactly does that mean? Exactly?

    Were they actually sick?
    Were they only exposed?
    If so, how many had symptoms?
    How many died?

    And most importantly, how does that compare to the normal flu that sweeps the nation every year. What percentage of the population tests “positive” for flu every year but doesn’t actually get sick. I’m assuming by testing positive they were lightly exposed, developed anti-bodies, but never got sick. Without the comparison data, we don’t know if 20% (or whatever number) is good, bad, whatever.

    And then, of course, you can’t even trust the raw data since it contains so many known errors. Yet we’re on lock-down, school is canceled, I gotta wear a mask, and they are primed to use mail-in voting to steal the election. I’m almost to the TINVOWOOT position because of this mess.

    Like many have said, there’s a switch. Vote, or shoot everyone.

  3. I had access to my dad’s HP 35 Scientific Calculator back in 1972. Having been weaned on RPN, to this day I can’t use the algebraic type.

    Also. In the military I was a mechanical maintenance officer. What your old boss did was a technique that was taught to us in training. They called it Command Maintenance Management Indicators, CMMI for short. When inspecting a platoon of tanks, for example, pick out some obscure thing such as checking for hydraulic leaks in a particularly hard-to-reach place. Next time pick something else. Keep the troops slightly off balance by their not knowing in advance what you are going to check that day. You have to remember that no combat ready unit would ever pass inspection.

    1. I learned in the military that doers do, what checkers check…

      And checkers check, what inspectors inspect.

      So, one airplane, I’d check one obscure thing, another on the second, third, etc….

      Never be predictable.

      1. …and one of the first things a grunt learns is that unless you are trying to win some award, you give the inspector a couple of easy things to hit. You fix those things quickly and he will go away.

        Why? You ask. Because too many inspectors are full of themselves and no matter how good you are, they will always find something.

        1. always give them something obvious to complain about / monkey with, or they will come up with something completely inane.

  4. A note from my past that shows how the media treats numbers. I’ll begin by saying that it has nothing to do with the virus, but I’ve always remembered how quotes from “authorities” (in this case me) get repeated as official.

    Our local university hosts a renaissance fair every spring and for many years our sheriff’s reserve unit assisted the university police with security. I always enjoyed working at the event because the people were eccentric enough to be interesting and the crowd was usually well behaved.

    This happened about 20 years ago. At the time I was in charge of our reserves and wearing captain bars on my collar. It was a Saturday afternoon and I was standing at the law enforcement command post telling lies with the chief of the university police.

    A reporter from the local newspaper approached us and asked how things were going. The chief stated that everybody was enjoying themselves and we hadn’t had any trouble. She then turned to me for some reason and asked “Captain, do you know how many people are here today?”

    I’ve never been very good at estimating crowd sizes and I really didn’t have a clue. I glanced over at the chief and made an offhand comment “What do you think Chief? I’d say about 30,000 or so” as I pulled a number out of my ass. He laughed and said “Yeah Dave I’d say that’s about right .” The reporter thanked us and wandered off.

    The next day the local paper ran a story that said “Authorities placed the crowd size at 30,000 people. This set a new record for fair attendance and was praised by the University President as a sign of the event’s popularity.”

    No harm done and I still laugh about it, but a good example of where “official” stats often come from.

    1. When I did cost estimations for aerospace many long years ago, we called your 30,000 participants number a PIDOOMA. When we needed a number and there was no way to get one with any pedigree, we did the same thing you did, and “Pulled It Directly Out Of My Ass.”

      1. PIDOOMA – I like that. It’s a close relative to “SWAG” – Scientific Wild Assed Guess.

  5. Remember the media is populated by people who never came close to any course that possibly might include any form of math. Their math education ended in the 8th grade when they managed to escape Algebra 1. The word came down from the top. Keep reporting on the number of cases as if we are waiting for the day that number total cases will start to go down again.

  6. The one that bugged me is that if a person tested negative, but died of symptoms indicative of COVID-19, they’re counted as a COVID-19 death. But are they then also counted as a COVID-19 CASE when determining death rate? If you add him to the numerator, you HAVE to add him to the denominator too.

    But explaining that requires too much math. Or honesty.

    1. There no false positives. Those people are listed as “Asymptomatic” and therefore “Very Dangerous” . I guess because they then spread their weak version of the virus which produces no symptoms to others unknowingly who then get the strong version.

      This, despite well publicized stories of people who were positive last week but now are cleared to participate in some sporting event.

      There are no false negatives either…… admitting that might lead to some people not believing what they are told to be the truth.

      ……. and why the focus on the total number of tests ….. what population are they testing? Is it representative of the entire population … or some subset. If they are primarily only testing people likely to be exposed multiple times and 98% come back negative and of the positive portion , only 5% OF THOOSE are hospitized …why are we doing this??

  7. I’ve heard this weekend that for whatever reason (incompetence, malfeasance, stupidity?) some jurisdictions are not testing for the presence of the virus, but testing for the absence. So, if someone is offered a test, and refuses it, they record the test as positive (“we cannot rule out the presence of the virus”).

    No idea if the contractors doing this are getting paid per….or what.

    But this explains the very high positive rates in some locations..

  8. Two weeks ago the death rate in Texas per day went over 100 and until today it has stayed high most of the time. Most of the deaths were in the border counties next to Mexico where there is a large uninsured population and I suspect that when the death is a COVID death there is government money Federal or State that pays the bill. If that is the case even gun shot victims start looking as if they might have a COVID related cause of death, $$$$$$$ and bring in the next one, yep smells like COVID on his breath, because hospital business has been slow.

  9. I was strictly RPN until I was packaged out of industry and became an engineering prof. My students all had TI-89’s so I had to buy one and learn how to use it so I could understand the details of how they calculated. I’m therefore sort of bilingual; I need a day or so to switch my brain from one to the other but I can use either. Is that lag common with spoken languages? If you speak both English and Spanish for example, do you need a day to get your brain fully into Spanish mode if you haven’t used it for a year or so?

    I’ve heard the “if one thing is wrong, trust nothing” principle called the Principal of the Thirteenth Knell. If a clock chimes thirteen times, the thirteenth knell is not only immediately recognized as false, but it casts considerable doubt on the validity of the preceding twelve.

    1. Aghhhhhh!
      I know the difference between principle and principal but my fingers don’t.
      And, obeying Murphy’s Law, the time for edits has expired.

    2. When I was traveling from Germany to France, the first couple of conversations I had with the Frogs resulted in me saying “Sehr gut” instead of “D’accord”, and “Stimmt das” instead of “C’est vrai” until my brain finally made the switch. Very frustrating.
      I also sometimes (still) answer question put to me in German with Afrikaans instead, because the languages are SO similar (“I’d lost my hat” –> “Ich hatte meinen Hut verloren” vs. “Ek het my hoed verloor”) and not having spoken German for so long, I kinda default to the language of my childhood.
      As I said, very frustrating.

  10. Another thing that may be skewing the statistics is, are they counting positive tests, or are they counting the number of people who tested positive?

    PawPaw on his blog cites where someone did a deep dive into small rural county in Louisiana. County health department had listed 96 positives. The deep diver counted actual names, and there were only 58 people who had tested positive. So 40% of the listed positives were coming from doing multiple tests on the same people, up to 4 times in some cases.

    And how many of those people who only tested positive once were actually false positives?

    That said, if the errors were truly random, they would move the arrow in both directions, and average themselves out. But when all the errors always seem to move the count upward – you begin to suspect someone is putting a thumb on the scale.

  11. Years ago I took a course in statistics. I learned a lot that anyone who cites statistics should know, but probably doesn’t. It was an eye opener to me as I never understood this field before, and I learned to mistrust many conclusions people would make based on their ignorance of statistics. My statistics professor had a stutter, and it was painful to hear him try to say the word “statistics”. I also remember one girl in the class had a very nice figure, just to make a pun and remind me of her…

    By the way, RPN calculators are the only way to go, and I see some kindred spirits here. I think I have had 8 different HP calculators through the years and still have, I think four left.

      1. Amen. It’s like saying “I down the street am walking.” Germans do it, but that doesn’t make it natural.

  12. Good Lord, man! I have trouble speaking my birth language (Amerilish,) so’s other folks can understand.

Comments are closed.