News for hackers. Stuff that matters.

A comment on 52 Years and $750 Million Prove Einstein Was Right. Parent comment

Re:52 Years and $750 Million Prove Einstein Was Right by lutorm on Thursday May 05, 2011 @03:01PM (#2518532)
What you are describing is a very real danger, but if you are modeling actual noise, it's less of a risk than if you are modeling some small systematic shift that you claim you must subtract from the signal. With noise, it's more unlikely that the model would just by chance give a systematic shift to the data. More likely, if the model is wrong, it just won't decrease the noise level.
[ Parent | on HN ]
Re:52 Years and $750 Million Prove Einstein Was Right by ars on Thursday May 05, 2011 @03:10PM (#2518558)
It's was actually systematic shift, but a periodic one. It wasn't random noise.
[ Parent | on HN ]
Re:52 Years and $750 Million Prove Einstein Was Right by lutorm on Thursday May 05, 2011 @03:33PM (#2518642)
Well, true. If the noise was truly random, you couldn't model it, of course. I just meant "noise" in the sense of "apparently random variations that actually aren't random".
[ Parent | on HN ]
Re:52 Years and $750 Million Prove Einstein Was Right by starwed on Friday May 06, 2011 @12:23PM (#2521405)
That's not quite true, since a small signal+random noise will certainly give you a prediction that is testable.
[ Parent | on HN ]