SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Microcap & Penny Stocks : ADVR:THE NEW COMPANY...WITH A NEW LIFE...AND A NEW MISSION

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: jmt who wrote (427)6/15/1998 12:56:00 PM
From: Kingfisher  Read Replies (3) of 4891
 
jmt....IMHO your reality check is involving too many aspects which may only have to be considered by
company managers not necessarily pseudo intellectual penny stock investors. After all, predictions
can border on the absurd like basing the direction of the Stock Market in a given year on the league
[NFL, AFL] of the team that wins the Super Bowl.

Predictive mathematical models can be simple [i.e. composed of only one or two parameters] or involved
[i.e., having many degrees of freedom]. Many of these later models use abstract mathematics
[e.g., algebra, calculus], can be based on complex principles and may incorporate assumptions which can
be flawed or not totally thought out. It would seem best that if one is attempting to make a prediction,
the number of model parameters used should be kept to a minimum.

Another point about modeling/prediction is that models can be fed data that are not obtained from accurate
absolute measures. And to top that, input data may even be the output data from another model.
Thus, if the input data for the model are flawed in any way, the output data will be erroneous.
In other words, GARBAGE IN IS GARBAGE OUT. The more parameters contained in a model
the greater the chances for GARBAGE IN.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext