Re: Problem related to a linear regression

I think for finding the best correlation it's probably better not to
include (u and v or A and B) since this is for this operation only
unnecessary payload and do the transformation afterwards, thus
separating the two operations correlation and transformation. This
leaves then also the choice to do the subsequent transformation the
preferred way, either by minimising dy^2 or dx^2 or ODR. (A side note:
minimising dy^2 results in a minimal standard deviation of Y having a
higher one for X; minimising dx^2 results in a minimal std dev of X
and having a higher one for Y. You gain on one side by losing on the
other.)

To you Matt and to all others who helped: many thanks!

Regards Marcel

.

Relevant Pages

  • Re: Problem related to a linear regression
    ... Regarding the correlation line: I'm not sure since we have the same ... possibly minimising absolute y-differences) makes more sense than ... obviating the need for the separate regression step. ... best linear relationship between Xf and Y. Then in the subsequent ...
    (sci.math)
  • Re: Is the Curt net a kind of decision tree?
    ... The two signals don't act as ... created by the network might have had something to do with the reward. ... If multiple pixels share a common correlation ... to the type of transformation these networks should be performing on the ...
    (comp.ai.philosophy)
  • Re: Problem related to a linear regression
    ... possibly minimising absolute y-differences) makes more sense than ... The regression line obtained by minimising the dx's also ... correlation can be 'matched' to the observed values Y? ... best linear relationship between Xf and Y. Then in the subsequent ...
    (sci.math)
  • Re: Wolframs rule 30 as a hash function
    ... no single transformation recipe for mapping input to output. ...  The computer program is the single recipe. ... Correlation example: The numbers are drawn from the hat 7, 4, 5,, ...
    (sci.crypt)
  • Re: r^2 and log transformation
    ... appropriate transformation of regression variables’, ... from a set of alternative regression specifications involving different ... the correlation of the log-y values with the ... when you take logs.) ...
    (sci.stat.math)