From: jimmyw836@gmail.com   
      
   On Friday, August 6, 2021 at 10:24:50 AM UTC-4, MrPosti...@kymhorsell.com   
   wrote:   
   > EXECUTIVE SUMMARY:   
   > - We can ask an AI "what is odd about the 1970s". Already we know the   
   > 1970s is a bit odd because it featured a rash of reports of cattle   
   > with their faces cut off across the western US. The reports got so   
   > thick even the FBI was called on to look at it.   
   > - The AI chugs away and spits out a list of known datasets that can be   
   > simply manipulated to finger the 1970s and no other years. The top   
   > fits include our old friends Saturn, Uranus and Flying Disks.   
   > - A lot of other data series can point out the 1970s, but they also   
   > tend to "ping" other years as well. The planets and UFO data are the   
   > "best explanation" the s/w can find.   
   > - The models found seem to agree very roughly -- given we asked a   
   > rather vague question.   
   > - The models also predict cattle mutilations -- if they are in fact   
   > related to Saturn, Uranus and Disks -- still continues at a lower   
   > level than the 1970s. We might also predict another big up-tick   
   > around the time when Saturn and/or Uranus again approach perihelion.   
   > The "Saturn" model says around perihelion -- 2002, then 2031.   
   > The "Uranus" model says around 10y after -- 2059.   
   > Did the 2002 peak (+-) happen?   
   >   
   >   
   > We've had a look at this before. But something the s/w has thrown up   
   > at me this week relates and is fairly interesting from an AI point of view.   
   >   
   > We recall we've looked at the "big FBI Report" into cattle mutilations   
   > in the 1970s. As an apologia for the "report", the FBI pointed out   
   > looking at butchered cows was not generally in its area of   
   > responsibility. Which might explain the rather sketchy document it   
   > produced in the 1970s that listed a couple dozen reports of animal   
   > mutilations with some additions at the end (the quality of the   
   > document when it got to the PDF-making stage makes it fairly unclear)   
   > written in what seemed to be pencil.   
   >   
   > We ran those numbers through my s/w and it did come up with an   
   > interesting list of possibilities for what best explained the pattern   
   > of dates seen in the report.   
   >   
   > But the s/w can do a bit more. AI's can answer "vague" questions as   
   > well as specific ones.   
   >   
   > Given cattle mutilations hit the headlines in the US during the 70s --   
   > some wikipedia pages say the rash of reports lasted from 1973-1983 --   
   > we could ask the program -- what is so strange about the 1970s?   
   >   
   > As we recall the s/w has a list of 10s of 1000s of datasets from   
   > various govt and NGO agencies around the world related to mostly   
   > weather and satellite observations, but also a lot of data on the   
   > evolution of economic data in rich and poor countries, plus all manner   
   > of other odds and sods the program has uploaded by using google/bing   
   > searches.   
   >   
   > So what is weird about the 1970s? We give the AI a dataset that shows   
   > years 1950-2020 with a 1 or 0 next to them depending on whether the   
   > year is "interesting" (i.e. within the 1970s) or not.   
   >   
   > It chugs away for a few mins and spits out a lit of datasets that   
   > "look similar" to the target data we gave it, along with some stats   
   > showing "how similar" it is. All the stats has been run through a few   
   > packages I trust and the s/w knows how to run and also how to   
   > interpret the text output (e.g. looking for error messages or unusual   
   > conditions in the output ASCII plots :) and have shown to be   
   > statistically significant in at least 2 ways better than 90%   
   > confidence (IOW 10% or less chance the relationship could be just due   
   > to chance).   
   >   
   >   
   > Suspect Lag R2   
   > (y)   
   > sdsaturn-v 1 0.78547796   
   > sduranus-v 10 0.77604360   
   > ufo-Disk 0 0.39706604   
   > preband80 10 0.28790204   
   > ant170 1 0.22532102   
   > minmoon-r 0 0.16713256   
   > preseg160 5 0.13669447   
   > minkenya 10 0.13381989   
   > cosmic-OULU 1 0.12696118   
   > minaravgArcocean 0 0.09475654   
   > stormseg-160 1 0.09380508   
   > lat-80 0 0.05671197   
   >   
   > Each line gives the name of a dataset in the code the AI uses, a   
   > number of years it uses to "lag" the suspect data to make it look   
   > closer to the target data (in this case the list of years 1970-1979)   
   > and the "explanation power" of the suspect data to predict whether the   
   > years listed are "interesting" or "not interesting".   
   >   
   > It claims the "sdsaturn-v" lagged by 1 year predicts around 78% of the   
   > interesting years.   
   >   
   > The 2nd line is a similar thing, but for Uranus, and lagged by 10   
   > years not 1. Kinda befits a planet that is much further out and has a   
   > longer orbit.   
   >   
   > And the 3rd item suggests sightings of "Disk" objects also predicts   
   > the 1970s around 40% of the time.   
   >   
   > It seems the program is suggesting the best explanation for the 1970s   
   > appearing in our list is "something to do with Saturn, maybe Uranus   
   > and Disk UFO's and maybe other things that look like predictors of   
   > western US winter weather"..   
   >   
   > Let's have a look at a couple of these in more detail.   
   >   
   > Here's the model for the "sdsaturn-v" dataset.   
   >   
   > (Serial corr detected; estimated rho = 0.671802)   
   > y = 0.137581*x + -0.220647   
   > beta in 0.137581 +- 0.0174059 90% CI   
   > alpha in -0.220647 +- 0.166409   
   > T-test: P(beta>0.000000) = 1.000000   
   > r2 = 0.78547796   
   >   
   > Dataset:   
   > (binned into decades for brevity)   
   > Decade av x av y av model-predicted y   
   > 1950 3.27411 0 0.229809   
   > 1960 3.42266 0 0.250246   
   > 1970 14.7949 4.08 1.81486   
   > 1980 3.25553 0 0.227251   
   > 1990 3.55803 0 0.268871   
   > 2000 3.89511 0 0.315246   
   >   
   > It shows the variable/model "predicts" years other than the 1970s   
   > should be 0, but the 1970s years should be modestly interesting.   
   >   
   > The interest part comes because Saturn reached its closest approach to   
   > the sun in 1973. This makes the variation of the "v" angle -- the   
   > angle between the planet's perihelion and current position in degrees   
   > -- suddenly switch from 360 to 0 during the year making the "stddev"   
   > quite large which is why the AI has spotted it. The stats don't think   
   > this can be a total coincidence. And, beside, nothing else it has   
   > does any better and most of it does a lot worse.   
   >   
   > Here's the model for the "Disk UFO" dataset.   
   >   
   >   
   > (Serial corr detected; estimated rho = 0.504612)   
   > y = 0.113894*x + -1.28638   
   > beta in 0.113894 +- 0.0313676 90% CI   
   > alpha in -1.28638 +- 0.324333   
   > T-test: P(beta>0.000000) = 1.000000   
   > r2 = 0.39706604   
   >   
   > Dataset:   
   > (binned into decades for brevity)   
   > Decade av x av y av model-predicted y   
   > 1930 1 0 -1.17248   
   > 1940 2.33 0 -1.02062   
   > 1950 7.78 0 -0.400535   
   > 1960 15 0 0.422033   
   > 1970 35.8 5.22 2.79103   
   > 1980 15.8 0 0.513149   
   > 1990 18.4 0 0.809273   
   > 2000 14 0 0.308139   
   >   
      
   [continued in next message]   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)