|
feldman114
Stragler


Registered: 09/06/19
Posts: 3,365
Loc: Bravos
Last seen: 3 years, 9 months
|
Re: The Federal Reserve [Re: Kryptos]
#26561225 - 03/27/20 01:53 PM (3 years, 9 months ago) |
|
|
Quote:
Kryptos said: We will never have 100% results on the mortality of the human race until the human race is extinct. Nothing is exact.
Statistics can't predict that you will die. Statistics can only predict when you will die. And that is based on other people, i.e. data points.
If you leave the group of data points, then there is no basis upon which to use statistics.
My point exactly We will never be 100% sure of a golf ball’s future trajectory. But there’s more basis to statistically predict my mortality than there is to predict a certain trajectory, simply because there were more experiments (deaths) than golf strokes.
But yes, nothing is exact. Not statistics and not physics....
|
Kryptos
Stranger

Registered: 11/01/14
Posts: 12,262
Last seen: 48 minutes, 28 seconds
|
Re: The Federal Reserve [Re: feldman114] 1
#26561269 - 03/27/20 02:18 PM (3 years, 9 months ago) |
|
|
Quote:
feldman114 said: But there’s more basis to statistically predict my mortality than there is to predict a certain trajectory, simply because there were more experiments (deaths) than golf strokes.
No, not at all.
Given our best measurement techniques, I can calculate where an average golf ball (45g) will land on an average swing (130mph) to at least within 10^-16 meters, probably closer to 10^-18 or 10^-19. That's without math, that's just looking at the planck constant. For comparison, a proton is 2*10^-15 meters wide. Compared to the average golf drive distance of 200m.
Given our best measurement techniques, I can be 95% certain that you will die between the ages of 48 and 108, if you were born this year.
Which one of those is more accurate, do you think? In my opinion, there's a reason that one of those two is used to kill people with artillery.
|
feldman114
Stragler


Registered: 09/06/19
Posts: 3,365
Loc: Bravos
Last seen: 3 years, 9 months
|
Re: The Federal Reserve [Re: Kryptos] 1
#26561310 - 03/27/20 02:42 PM (3 years, 9 months ago) |
|
|
You can be 100% certain you will die.
Based on billions of people of whom 0 turned out to be immortal.
I never mentioned age groups in any of my poasts. I’m just saying that statistics can predict my mortality with unmatched accuracy. Idk of any other experiments that were reproduced billions of times with 100% accuracy.
Certainly not ballistic missile tests. Or are you suggesting there have been more than 100 billion tests?
|
Falcon91Wolvrn03
Stranger



Registered: 03/16/05
Posts: 32,557
Loc: California, US
Last seen: 4 months, 21 days
|
Re: The Federal Reserve [Re: Kryptos] 2
#26561381 - 03/27/20 03:16 PM (3 years, 9 months ago) |
|
|
Quote:
Kryptos said:
Quote:
Falcon91Wolvrn03 said: So you see, you can have a larger N with a larger standard deviation.
Yes, and one of those standard deviations is more useful than the other when it comes to confidence intervals, t tests, and f tests. The one with the larger N.
Again, not true. If we assume a standard normal distribution curve (which I realize doesn't quite apply here), we see that
Confidence interval = μ +- (confidence level z value) * σ / √N
From this formula, we see that σ is more important than N in determining confidence interval.
Again, I realize we're not quite looking a normal distribution curve, but you should see the point.
-------------------- I am in a minority on the shroomery, as I frequently defend the opposing side when they have a point about something or when my side make believes something about them. I also attack my side if I think they're wrong. People here get very confused by that and think it means I prefer the other side.
|
Falcon91Wolvrn03
Stranger



Registered: 03/16/05
Posts: 32,557
Loc: California, US
Last seen: 4 months, 21 days
|
|
Quote:
feldman114 said: You can be 100% certain you will die.
Based on billions of people of whom 0 turned out to be immortal.
-------------------- I am in a minority on the shroomery, as I frequently defend the opposing side when they have a point about something or when my side make believes something about them. I also attack my side if I think they're wrong. People here get very confused by that and think it means I prefer the other side.
|
SirTripAlot
Semper Fidelis



Registered: 01/11/05
Posts: 7,459
Loc: Harmless (Mostly)
Last seen: 4 hours, 58 minutes
|
|
If you cant prove it with statistics, you are not trying hard enough.
-------------------- “I must not fear. Fear is the mind-killer. Fear is the little-death that brings total obliteration. I will face my fear. I will permit it to pass over me and through me. And when it has gone past I will turn the inner eye to see its path. Where the fear has gone there will be nothing. Only I will remain.”
|
Brian Jones
Club 27



Registered: 12/18/12
Posts: 12,340
Loc: attending Snake Church
Last seen: 2 hours, 57 minutes
|
|
Here's the way I'm thinking about in terms of the original issue of whether life expectancy at 60 is less accurate than life expectancy at birth. Given the large number of 60-90 year old's N is irrelevant. In survey research an N=200 is commonly used for a state survey and N=500 is commonly used for a national survey. Since we are talking about N in the millions, it's effects on accuracy will be many many decimal places to the right of zero in what ever measure we use.
That means that variability is the key issue effecting the accuracy of the estimate. How much variation is there in life expectancy at birth vs life expectancy at 60? Obviously if we use raw scores of standard deviation there is more variation in life expectancy at birth than life expectancy at 60. If we use standardized (Z-scores) I'm not sure if that difference remains or if they become more equal. I haven't done this stuff for a living for over 25 years. But since life expectancy is always expressed in years, that's a raw score. So it makes sense to use raw scores for the standard deviation.
Therefore, I am concluding that life expectancy at 60 is a more accurate measure than life expectancy at birth. If I'm wrong I'm still willing to bet $ that it isn't less accurate.
-------------------- "The Rolling Stones will break up over Brian Jones' dead body" John Lennon I don't want no commies in my car. No Christians either. The worst thing about corruption is that it works so well,
Edited by Brian Jones (03/28/20 03:08 AM)
|
Falcon91Wolvrn03
Stranger



Registered: 03/16/05
Posts: 32,557
Loc: California, US
Last seen: 4 months, 21 days
|
|
Quote:
SirTripAlot said: If you cant prove it with statistics, you are not trying hard enough.
Was that directed at me? I just showed all the equations.
-------------------- I am in a minority on the shroomery, as I frequently defend the opposing side when they have a point about something or when my side make believes something about them. I also attack my side if I think they're wrong. People here get very confused by that and think it means I prefer the other side.
|
SirTripAlot
Semper Fidelis



Registered: 01/11/05
Posts: 7,459
Loc: Harmless (Mostly)
Last seen: 4 hours, 58 minutes
|
|
Just an overly simplistic comment for the community.
-------------------- “I must not fear. Fear is the mind-killer. Fear is the little-death that brings total obliteration. I will face my fear. I will permit it to pass over me and through me. And when it has gone past I will turn the inner eye to see its path. Where the fear has gone there will be nothing. Only I will remain.”
|
|