SIGforum.com    Main Page  Hop To Forum Categories  The Lounge    How to Correlate Data
Go
New
Find
Notify
Tools
Reply
  
How to Correlate Data Login/Join 
Member
posted
A couple of families we know have kids with autism, all born between the late-80's / mid-90's. I was reading an article on GMO's, which stated that GMO's have been offered since that timeframe. The article also stated that Italy has banned GMO's. Looking at what data I could get a hold of, Italy has not had the rise in autism as the U.S. has.

So, with that, does anyone know where I could get good data to see if indeed there is a correlation, and how to process the data? I'm not looking to start a conspiracy theory, the question just popped up while I was reading the article.

Thanks in advance.
 
Posts: 86 | Location: South Florida | Registered: April 12, 2015Reply With QuoteReport This Post
No More
Mr. Nice Guy
posted Hide Post
You would have to control for many factors. Diet, climate, ethnicity, injected products, parents's medical history, age, etc etc. Both statically and over time. Merely finding a correlation is meaningless. It would be an enormous project.

There is a clear correlation with the childhood jab schedule in this country. Even so, properly teasing out whether there are other factors has occupied researchers for years.

This is why so much "science" is total junk. Even well performed retrospective analysis has a 1 in 20 chance of being wrong by random coincidence, and most studies are not well performed.
 
Posts: 9709 | Location: On the mountain off the grid | Registered: February 25, 2002Reply With QuoteReport This Post
paradox in a box
Picture of frayedends
posted Hide Post
I doubt it's the GMOs specifically. More likely the increased use of Glyphosate that GMOs made possible.




These go to eleven.
 
Posts: 12598 | Location: Westminster, MA | Registered: November 14, 2006Reply With QuoteReport This Post
Void Where Prohibited
Picture of WaterburyBob
posted Hide Post
That's probably impossible to do.

Diagnosing and data collection parameters are probably not the same in Italy as here.

There are many other changes since the 80's that could also be involved; just to name a few:
gas additives changed in the 80's; suburban use of pesticides in this country is much greater since then; microplastics in the environment are much greater.

The rise in autism is probably caused by many environmental factors.



"If Gun Control worked, Chicago would look like Mayberry, not Thunderdome" - Cam Edwards
 
Posts: 16628 | Location: Under the Boot of Tyranny in Connectistan | Registered: February 02, 2005Reply With QuoteReport This Post
Fighting the good fight
Picture of RogueJSK
posted Hide Post
Even if you were to establish correlation, correlation alone is meaningless. For example, the rise of autism cases since the 1980s also correlates with a decline in the number of Presidents named Ronald, a lack of Super Bowl wins by the Raiders, and a rise in global beer prices. But one can safely say that none of those factors cause autism, despite the clear correlation. Big Grin

As noted, there are innumerous other potential causal factors besides just GMOs, as well as countless interrelations between all the various factors, that would have to be examined as well. This is a massive and extremely challenging undertaking. Nigh-impossible.

Establishing that GMOs cause autism is not going to merely be a side hobby for a bored retiree casually crunching numbers on his iPad on a lazy Sunday afternoon. Wink
 
Posts: 32992 | Location: Northwest Arkansas | Registered: January 06, 2008Reply With QuoteReport This Post
Staring back
from the abyss
Picture of Gustofer
posted Hide Post
quote:
Originally posted by WaterburyBob:
The rise in autism is probably caused by many environmental factors.

And non-environmental factors. Nowadays, "autism spectrum" diagnoses range from the kid who daydreams to Rainman. The rise in these diagnoses is similar (in dates and numbers) to the rise in ADD/ADHD diagnoses...many of which are BS.

That said, I do believe that the shit we are putting in our bodies, in the form of endocrine disrupting chemicals, have a definite negative effect and it's not just with autism. Breast cancers, cervical cancers, colon cancers, Alzheimers...while these certainly have existed in the past, the numbers pre-1940s-50s are minimal compared to today. There's a reason for that.


________________________________________________________
"Great danger lies in the notion that we can reason with evil." Doug Patton.
 
Posts: 20520 | Location: Montana | Registered: November 01, 2010Reply With QuoteReport This Post
Political Cynic
Picture of nhtagmember
posted Hide Post
That will be a huge, if not almost an impossible task.

As others have said there are a huge number of contributing factors - and an equally large number of factors that may not even be relevant.

I do not believe that you will be able to gather enough data on all of the factors to be able to do a proper analysis to either rule something in or out. With any degree of certainty.

And remember that data without context is pretty much meaningless in this. You can have all the data and data sets in the world but if you don’t know the context you cannot use it.

For all you know you might end up proving that priests are more likely to have children out of wedlock than grocery store check outs
 
Posts: 53750 | Location: Tucson Arizona | Registered: January 16, 2002Reply With QuoteReport This Post
Optimistic Cynic
Picture of architect
posted Hide Post
quote:
Originally posted by frayedends:
I doubt it's the GMOs specifically. More likely the increased use of Glyphosate that GMOs made possible.
There's another correlation that is even more closely represented. The rise in Autism/ADHD diagnoses correlates especially closely with the diminishing of coal burning. It has been speculated that this has resulted in a lowering of the prevalence of Arsenic in the air. It is known that insufficient Arsenic in the diet of children leads to delayed brain development.

This may also be a factor as to why Chinese and other countries that are still burning coal seem to have kids that outperform ours in math and other demanding educational subjects.

OTOH, maybe there is just more diagnoses of incidence than the actual incidences themselves due to a lesser onus attached, the economics of a whole industry built to serve the diagnosed, or some other factor unrelated to biological/environmental factors.
 
Posts: 6740 | Location: NoVA | Registered: July 22, 2009Reply With QuoteReport This Post
Political Cynic
Picture of nhtagmember
posted Hide Post
the biggest hurdle you will face in your quest for data is that you will never know how the data was collected.

bias - inherent or unintentional can come from several factors - how was the question phrased? What was the preceding question - did its answer lead to a predetermined response for the next question. did the data collector have any biases in how the data was collected or did he/she/they/it even have an agenda in mind when they prepared the study

all of those things are unfortunately out of your control
 
Posts: 53750 | Location: Tucson Arizona | Registered: January 16, 2002Reply With QuoteReport This Post
Member
posted Hide Post
A visual clue on just how involved it can be, I like to refer to http://www.tylervigen.com/spurious-correlations


--
I always prefer reality when I can figure out what it is.

JALLEN 10/18/18
https://sigforum.com/eve/forum...610094844#7610094844
 
Posts: 2383 | Location: Roswell, GA | Registered: March 10, 2009Reply With QuoteReport This Post
Member
Picture of wrightd
posted Hide Post
good point. by itself correlation <> causation.




Lover of the US Constitution
Wile E. Coyote School of DIY Disaster
 
Posts: 8906 | Location: Nowhere the constitution is not honored | Registered: February 01, 2008Reply With QuoteReport This Post
Member
posted Hide Post
Thanks to everyone for your replies, much appreciated.
 
Posts: 86 | Location: South Florida | Registered: April 12, 2015Reply With QuoteReport This Post
Member
posted Hide Post
After reading each of the above posts, I am left with the pertinent physics axiom: The rain in Spain lies mostly...
 
Posts: 58 | Location: north-central Florida | Registered: February 12, 2021Reply With QuoteReport This Post
His Royal Hiney
Picture of Rey HRH
posted Hide Post
What you're looking for is a regression analysis that can be done on Excel and is pretty simple to do. The data just needs to be supplied.

How it works is you get the data of what you are interested in, in your case incidences of autism.

The easiest first set of data would be date related. Birth dates and for each birth date, number of children that were diagnosed with autism. Those then can easily be parsed into months, years, seasons, etc. Next would be geographic information. You might also get data on prescriptions the mothers may have been taken. So far, each record or row would be:

Qty of Autisms, birthdate, Address, Mother's Prescription A, Mother's Prescription B, Mother's Prescription C

That allows 3 separate prescriptions to be identified and either a value of 1 for yes or 0 for no.

You can come up with all other possible possible drivers as to what you suspect may possibly drive autism.

You let the spreadsheet or any actual statistical program process the number and it spits out a number to associate with each possible driver. The higher the number means a higher correlation of autism with that suspected driver. It can also come up with negative correlation values.

You do need human eyes to make sure the correlations make sense.



"It did not really matter what we expected from life, but rather what life expected from us. We needed to stop asking about the meaning of life, and instead to think of ourselves as those who were being questioned by life – daily and hourly. Our answer must consist not in talk and meditation, but in right action and in right conduct. Life ultimately means taking the responsibility to find the right answer to its problems and to fulfill the tasks which it constantly sets for each individual." Viktor Frankl, Man's Search for Meaning, 1946.
 
Posts: 19992 | Location: The Free State of Arizona - Ditat Deus | Registered: March 24, 2011Reply With QuoteReport This Post
thin skin can't win
Picture of Georgeair
posted Hide Post
I think you have to ask yourself "To what end?" as well.



You only have integrity once. - imprezaguy02

 
Posts: 12641 | Location: Madison, MS | Registered: December 10, 2007Reply With QuoteReport This Post
Member
posted Hide Post
quote:
Originally posted by PPinesRon:
A couple of families we know have kids with autism, all born between the late-80's / mid-90's. I was reading an article on GMO's, which stated that GMO's have been offered since that timeframe. The article also stated that Italy has banned GMO's. Looking at what data I could get a hold of, Italy has not had the rise in autism as the U.S. has.

So, with that, does anyone know where I could get good data to see if indeed there is a correlation, and how to process the data? I'm not looking to start a conspiracy theory, the question just popped up while I was reading the article.

Thanks in advance.


Your question ignores the differences between two different Nations on how Autism is defined. That can have a significant effect on the "observed rates of Autism". For example the USA has gone fully Woke on Autism and they tend to define a lot of personality quirks as Autism. I expect that in Italy the children diagnosed as Autisitic are those who have a rather severe personality disorder. One is Asperger's, here in the US that is considered as Autism. I expect that in Italy these children are NOT considered as Autistic, they are considered as high IQ individuals with a mild bit of OCD. If you want examples of this there is George Eastman, Thomas Edison, Henry Ford, and Albert Einstein and I expect a very long list of high achievers who made significant contributions to Society.


I've stopped counting.
 
Posts: 5765 | Location: Michigan | Registered: November 07, 2008Reply With QuoteReport This Post
  Powered by Social Strata  
 

SIGforum.com    Main Page  Hop To Forum Categories  The Lounge    How to Correlate Data

© SIGforum 2024