John Edser wrote:
>>>BOH:-
>>>The problem was refuting a random pattern without making any assumptions 
>>>about the process.  It's the same question I have been asking for a few 
>>>posts. 
> 
> 
>>>JE:-
>>>Perceptual pattern types are just, defined.
>>>Only two most basic pattern types are defined to exist
>>>within nature where one type entirely excludes the other, 
>>>i.e. no perceived pattern can be both types, simultaneously.
>>>These most basic types are: random and non random patterns.
>>>A random pattern is refuted when it is a non random
>>>pattern and vice versa. 
> 
> 
> 
>>BOH:-
>>But, to continue to try and get an answer, how do you decide whether a 
>>pattern is random or not?
> 
> 
>>JE:-
>>By definition.
> 
>  
> 
>>BOH:-
>>To give a concrete example, how would you decide whether the following 
>>sequence of 30 numbers is random?
>>  2  6  2  1  5  8  1  4  2  3  5  4  6  6  5  5  5  7  4  5  7  4  3 10 
>>  6  3  6  7  6  5
>>
>>JE:-
>>By definition.
> 
> 
> BOH:-
> Which makes it impossible to refute.
> 
> JE:-
> Incorrect! ANY definition provided 
> must be a part of refutable proposition
> of nature, i.e. be a part of a fully
> testable scientific _theory_.

Ah, so you do have to have a process - that's what the theory defines.

> The absolute assumption of the proposition
> is the refutable part of any proposition.
> This absolute assumption must be defined
> and be testable.
> 
> Just because you can define a random pattern
> to be any pattern you like, does not mean that:
> 
> 1) All such definitions allow a testable proposition
> of nature.
> 
> 2) Each proposition is equal in its ability to explain
> nature.
> 
> Science is not anarchy, but does embrace a total freedom to 
> imagine. What has been imagined must be put to the rigor 
> of testing. If you delete refutation then testing becomes 
> impossible and science ceases to exist. 
> 
> The normal definition of a random process as any process that
> can only cause a random pattern, 

Not true - you're the only person I've seen ever using that definition.

allows the proposition
> of a random process to be refuted but not verified because 
> a _non_ random process can cause both basic pattern 
> types. The point of the exercise is to be able to 
> separate a significant observation from a non significant
> observation. If science can't do this then science can't
> observe anything.
> 
I would suggest you look into the literature on statistical analysis and 
stochastic proceses.  We can do all this, and more.  It appears to me 
that you're wholly ignorant of data analysis, and hence don't have any 
idea about how to actually test for randomness, or indeed what "random" 
means within mathematics and the sciences.

Bob

-- 
Bob O'Hara

Rolf Nevanlinna Institute
P.O. Box 4 (Yliopistonkatu 5)
FIN-00014 University of Helsinki
Finland
Telephone: +358-9-191 23743
Mobile: +358 50 599 0540
Fax:  +358-9-191 22 779
WWW:  http://www.RNI.Helsinki.FI/~boh/
---
þ RIMEGate(tm)/RGXPost V1.14 at BBSWORLD * Info{at}bbsworld.com

---
 * RIMEGate(tm)V10.2áÿ* RelayNet(tm) NNTP Gateway * MoonDog BBS
 * RgateImp.MoonDog.BBS at 12/27/03 8:11:24 PM