| reply to Linklist
Re: Past statistics don't always show future trends said by Linklist:Those predicting drastic growth may be more prescient than the statisticians looking backward. I have a very serious problem with that statement and here's why.
I took statistics and probability. If there's anything I learned out of that class is that statisticians look at past data to make predictions about future trends. Without past data, there is no baseline for them to show future trends.
You can't have one without the other. You got to have past data to create any statistical trends at all regardless if the trend is accurate or not, period.
--
Be careful who you vote for, you just might get it. |
|
 LinklistPremium
join:2002-03-03
Longport, NJ
kudos:5 | said by Nightshade:I took statistics and probability. If there's anything I learned out of that class is that statisticians look at past data to make predictions about future trends. Without past data, there is no baseline for them to show future trends. You can't have one without the other. You got to have past data to create any statistical trends at all regardless if the trend is accurate or not, period. So did I. And there is no statistical models that project when the knee in a curve may happen. And that is what you can't predict based purely on past trends.
--
My BLOG .. .. Internet News .. .. My Web Page
Ask yourself one question: 'Do I feel lucky?' Well, do ya punk? |
|
1 edit | Oh I know. If anything creating statistics is really a combination of mathematical theory and good old fashioned educated guessing. All statistical models will eventually fail, it's just a matter of when and how the data that already exists is modeled. But you still need strong past data to make the predictions. Without that all you really are doing is doing baseless guessing.
--
Be careful who you vote for, you just might get it. |
|
|
|
