Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
NCTM or The Math Forum.


Math Forum
»
Discussions
»
sci.math.*
»
sci.math
Notice: We are no longer accepting new posts, but the forums will continue to be readable.
Topic:
regressions
Replies:
4
Last Post:
Sep 28, 2017 9:59 PM



Bill
Posts:
772
Registered:
8/11/13


Re: regressions
Posted:
Sep 28, 2017 4:42 PM


RichD wrote: > I attended an economics conference recently, they covered > the usual stuff; growth, trade, interest rates. There was > frequent use of the phrase "run your regressions, blah blah". > > What does this mean? If you have a bunch of data (x, y), where x may be tuple (x1, x2,..,xn), a regression analysis will find the "best linear approximation of y" based upon the data. "best" in the sense that it minimized the square of the errors (note: none of the data points may actually lie on the "line". In your situtation, look in any book with "Econometrics" in the title for the full story! Or just look here, for a nice example, with a diagram:
https://en.wikipedia.org/wiki/Econometrics
Bill
> > >  > Rich



