17 Comments

With regards to slowing Science down, the classic response from Augustine sums it all up. 'It is better to limp in the right direction than to run in the wrong direction at great speed.'

Expand full comment

Only to add ...

Which is why it is better to enter THE KINGDOM OF HEAVEN one eyed than ending up in THE LAKE OF FIRE...

Expand full comment

"The fix? There is no fix."

Or if there is, it is a human one and has nothing to do with statistics. They simply have to be able to admit - to themselves and the world - that they don't understand the things they claimed they understood, a claim their self-esteem was dependent on.

In industrial R&D when you create a model and it doesn't work, you can't say it was "peer reviewed" - the customer just sends the machine back, and someone asks you why your model sucks. I imagine academics regard this process as an annoyance, when in fact subjecting your model to unseen numbers and circumstances is usually the only way work out what is really going on. They are like a sofa musician versus a performing one - much much worse than they think they are.

Expand full comment

"Or if there is, it is a human one and has nothing to do with statistics."

ABSOLUTELY - ... but the issue being THE HUMAN MIND so LOCKED UP in its own MENTAL PRISON CELL one can only call PRIDE it is "humanely" impossible to come out of THE IVORY TOWER THE CULT OF LIES operates out of ... add THE TOWER OF HUBRIS based on THE FIAT CURRENCY PONZI SCHEME around THE WORLD and should give EVERYONE shivers what the world is facing.

Here is a little clip that I graciously stumbled upon, which is a showpiece of THE HUBRIS this comment is referring to:

https://www.bitchute.com/video/61Q9mTBu2n6N/

Expand full comment

is it not statistically significant

that 4 large commercial airliners disappeared upon crashing and all on the same day?

Expand full comment

As @sauvagepen said in his restack, the map is not the territory.

Or put another way, when discussing different models of the atom in college physics, and yeah, it's also a paraphrase, none of the models of the atom are correct, they're just useful to one degree or another.

It's why I treat "science" as just so stories, and engineering as something repeatable (do "A", then "B" happens) even if we don't have an explanation as to why. Lots of times we know we CAN do something a certain way, but not why. Scientific hypotheses are just a narrative of expected behavior, "the system behaves as if."

It's a lot easier to create a narrative and fudge the numbers if you know what results you want ahead of time.

Expand full comment

This article and the studies mentioned and used as the bedrock to dismantle the paradigm of THE SYNAGOGUE OF SATAN posturing as "the science" is testimony to THE TRUTH being the only one that PREVAILS!

Even without these studies - by LOGOS applying REALITY - prove how futile THE SYNAGOGUE OF SATAN'S attempt is to posture as GOD ALMIGHTY. By observing REALITY an attentive, humble HUMAN MIND can "easily" discern between TRUTH and LIE. For example knowing that EVERYTHING influences EVERYTHING one necessarily has to come to the conclusion that, whenever you make one parameter "stationary" - no matter how big the sample is - the only result can be a PROBABILITY as according to REALITY - feedback loops of a closed system - it cannot be otherwise than that the REAL POSSIBILITIES - REALITY - will always be INFINITE!

Anyone ever tried to build an excel model where all parameters are "free floating" ... a challenge that I would bet ANYTHING against, that not even BILL THE DELUDED, with all his FIAT CURRENCY based on his DELUSION could fix ...

Expand full comment

We all know blue tits will suffer in a nest with more siblings competing for food on a planet in which all species are threatened by catastrophic ornithogenic global warming, so I predict that the vast majority of studies will find a negative effect. They did. My model is skillful and useful.

We all know nobody cares about eucalyptus seedlings, except to determine whether the grass or the eucalyptus should offer a land acknowledgement, so I predict that the studies will find no effect...

Expand full comment

As an aside, my background is in applied psychology (in hindsight probably not the best college major I could have picked) so I am aware of the problems plaguing the field of psychology research.

Recently I have been interested in nutrition and health. I watch a lot of videos from Bart Kay https://www.youtube.com/@bart-kay who is quite knowledgeable about statistics and research. It would appear the field of epidemiology as applied to nutrition and health outcomes is quite flawed either because of the limited statistics that can be employed and/or dishonest people who will, for example, claim RISK when their studies only show associations.

Expand full comment

There's an article today by James Moodey, who owned a "Weights and Measures gas-physics test-and-repair facility...." His company "conducted tests. We learned gas physics from engineers at factories that manufacture gas-physics instruments. They must understand gas physics or their instruments won’t work." He considers the Science of Global Catastrophism, and debunks it with reality.

Is Moodey's approach to science, testing and reality-based observations, the answer to wee-pee Science?

It doesn't seem he's doing any statistical maneuvering, but rather deriving calculus.

https://www.lewrockwell.com/2023/11/no_author/carbon-dioxide-does-not-cause-warming-no-gas-causes-warming/

Moodey's professional work was based on reality, testing gas to determine their properties--including how well various gases "hold heat."

Moodey says:

"Nearly everything we have heard about global warming for the past thirty-five years has been from the professorial world, which has been untested theory. How often have their declarations and predictions come true? Because their world is theoretical, they use peer review for approval.

There is no such thing as peer review in the private sector; something either works or it does not, and everything is tested. Engineers who design gas-physics instruments must be correct, or their instruments fail, buildings might burn, and they certainly would be fired."

Expand full comment
author

Kent,

That's it. That's real science: either it works or it doesn't.

Expand full comment

Which is why "social engineering" is neither social nor engineering. Which is why what you are describing is the perfect example how THE CULT OF LIES is using REALITY as a fig leave by twisting, turning and obscuring it till it fits its NARRATIVE of gaining worldly influence, material benefit ... no matter what the consequences - especially to "themselves".

"They" have deluded themselves into oblivion BELIEVING "they" are able to conjure up a world out of their fantasy/models ... not realising "they" are simply SERVANTS like any other CREATURE ... for THE TRUTH!

Expand full comment

If I understand you correctly, statistics are useful only if they have “predictive ability” with unseen real world data - is that right?

Expand full comment
author

Dave,

For the most part, yes. They can give hints about underlying causality, which is useful, but stats models can never prove it.

Expand full comment

Some questions for you. I apologize if you already answered this in your book as I have not had a chance to read it.

>The fix? There is no fix. There is a slight repair we can make, by acknowledging the conditional nature of probability, that it is only epistemological, that at a minimum the only way to trust any statistical model is to observe that it is has made skillful (a technical term) useful (a technical term) predictions of data never before seen or used in any way.

Question 1: Which specific statistical practices do you believe should be deprecated?

Question 2: How do you propose quantifying uncertainty without using statistical models? Furthermore, how could uncertainty in real-world propositions be quantified without the use of models?

Question 3: What type of evidence or studies could alter your opinion that significant changes are needed in the way statistics is practiced?

Question 4: What specific recommendations do you have for how researchers can better convey that statistical findings are contingent on modeling assumptions?

Expand full comment
author

Thanks for these. If my memory doesn't fail me, I'll answer these with a separate article.

Expand full comment
Comment deleted
November 6, 2023
Comment deleted
Expand full comment

"There are no coincidences" . . . I assert that the events of 9/11/2001 involved no coincidences

only a well-planned & executed fraud.

Expand full comment