Our perception of audio

[Blumlein 88]

A more modern dilemma with more than two players...

Oh one of my all time favorite movies. Have it on DVD though I don't think there are any complete copies of the original movie as I saw it back then.

 

[Soniclife]

EDIT: And here’s a more surprising, «savant» twist to statistics and observations: https://en.m.wikipedia.org/wiki/Monty_Hall_problem

I love that story, only in part because it involves lots of clever people being wrong, what are the odds of that.

 

[Brad]

One of the original motivations for Kahneman and Traversky’s research was the observation that professional statisticians didn’t seem to have an intuition for statistics

 

[Thomas savage]

I love that story, only in part because it involves lots of clever people being wrong, what are the odds of that.

Well if you read the forum those odds take another hit

 

[Theo]

Maybe, they should do this as a sighted experiment? That would improve the odds and become intuitive, wouldn't it?

 

[Fitzcaraldo215]

One of the original motivations for Kahneman and Traversky’s research was the observation that professional statisticians didn’t seem to have an intuition for statistics

Neither do most others.

 

[Cosmik]

I think understanding statistics is key. And by understanding I don’t mean formulas, tables and so on. Statistics is a state of mind where we replace magic by observations and observations by simple arithmetics, heuristics.

I don't quite know what you're getting at there. When you stress understanding, my immediate thought is that anyone who truly understands statistics would probably distrust the use of statistics in anything but pure mathematical puzzles. As soon as you try to apply them to complex, interesting real life you are making assumptions that are really just guesswork. These give you the financial crashes, and self-driving car crashes, that the statistics don't predict.

Statistics, like all mathematical disciplines, does not infer valid conclusions from nothing. Inferring interesting conclusions about real statistical populations almost always requires some background assumptions. Those assumptions must be made carefully, because incorrect assumptions can generate wildly inaccurate conclusions.

https://en.wikipedia.org/wiki/Statistical_assumption

To me, the highlighted text is just a fancy way of saying that you should think hard about your hand waving before attempting to justify the statistical approach you have taken. What follows may be extremely rigorous and mathematical but ultimately founded upon hand waving.

 

[svart-hvitt]

I don't quite know what you're getting at there. When you stress understanding, my immediate thought is that anyone who truly understands statistics would probably distrust the use of statistics in anything but pure mathematical puzzles. As soon as you try to apply them to complex, interesting real life you are making assumptions that are really just guesswork. These give you the financial crashes, and self-driving car crashes, that the statistics don't predict.

https://en.wikipedia.org/wiki/Statistical_assumption

To me, the highlighted text is just a fancy way of saying that you should think hard about your hand waving before attempting to justify the statistical approach you have taken. What follows may be extremely rigorous and mathematical but ultimately founded upon hand waving.

@Cosmik , my point is that statistics - not as a university course - but as an intuitive way of handling the complicated and the complex is underestimated.

I like the claim that «neutrality is a safe choice». To me, this is statistics. And I see it as clear as I can laugh when hearing a joke. «What was the joke?», the savant asked.

Above, I used the words «complicated» and «complex» on purpose. I think university courses in statistics teach you to quantify the complicated. However, when the complicated is replaced by the complex, concentional statistical tools become useless. And so the expression a fool with a tool comes to mind.

Audio is a mix of the complicated and the complex. Which serves as a reminder of when to trust the tools and when to trust experience, intuition and common sense. This is not to say that experienced people guided by intuition is a guaranteed recipee for success.

In another thread I asked people if they were objective oriented or subjective oriented on a scale from 1 to 5 where 5 is the most objective. My answer (on my own question...) is that this scale is meaningless in a dynamic process. When I start to look at a problem, I am a 5, i.e. the most objective. When the problem has been narrowed down using objective criteria, I become more subjective. What is the colour of the cable?

When I meet problems that I have extensive experience with, this is an effortless process where the steps from 5 to 1 (after some back and forth, maybe) is a gradual, not a rules based one. Trying to describe how I work on the different stages would be difficult if I couldn’t use the concept of « statistics» in a broader sense.

 

[svart-hvitt]

Neither do most others.

I could argue that the framing of questions can make people look stupid. When questions are framed in another way, people may not be as stupid as some scientists will have us to believe.

 

[Wombat]

I could argue that the framing of questions can make people look stupid. When questions are framed in another way, people may not be as stupid as some scientists will have us to believe.

Or as stupid as subjectivists would like to think scientists are.

 

[SoundAndMotion]

Or as stupid as subjectivists would like to think scientists are.

... scientists or engineers?

 

[Sal1950]

Or as stupid as subjectivists would like to think scientists are.

 

[Wombat]

... scientists or engineers?

And/or.

 

[SoundAndMotion]

And/or.

Fair enough.
But I think subjectivists have more problems with engineers than scientists.

 

[Wombat]

Fair enough.
But I think subjectivists have more problems with engineers than scientists.

Only the ones that disagree with them.

 

[Thomas savage]

Engineers are more practical?

Hairier..

 

[SoundAndMotion]

Only the ones that disagree with them.

I suspect roughly equal numbers disagree with them... it's how they disagree that's different.

Hairier..

Hairier than me?! Make sure they've had their shots! (Whiskey, not immunizations!)

 

[Theo]

To me, statistics are a just a tool designed to guide/improve our choices/decisions, they are not an absolute truth. For example, in the Monty Hall example, 1/3 of the guys who do not switch will (probably) lose, which will make them say that it does not work! Most of us (me included) like to trust something to be true; humans, even hairy engineers or bald scientists, don't like maybe's... Astrophysicists speak of dark matter as if it exists while they are still trying to find it? Or subjectivists say that the color of the cable makes a huge difference...

 

[Arnold Krueger]

Fair enough.
But I think subjectivists have more problems with engineers than scientists.

Likely true, but for a reason that seems low on insightful content.

There are generally far more engineers than scientists.

I think this is similar to the fact that people in the US have a lot more problems with GM cars and Dell computers than many others for the same reason. The reason is that there are simply so many more Dell computers and GM cars in the US to have problems with. They may even be more reliable, statistically. Or not.

This is particularly true because the word "engineer" is used so indiscriminately these days - "Engineer" is commonly used to identify a wide range of occupations ranging from operators of moderately complex equipment or that for which human life is at stake including boiler operators, to people who are probably more accurately identified as scientists.

 

[SoundAndMotion]

Hmm...
I tried a couple of light-hearted, tongue in cheek jabs at engineers... didn't work.
I didn't intend an exact tally of the number of problems!
FYI, in the US, there are about 3 times as many engineers as scientists, GM has about 19% of the market and Dell is #3, after HP and Lenovo, but ahead of Apple.
Doesn't change a thing about what I said.