Why not leave the small x's and y's as they are (not take their logarithms), and try to figure out a good enough equation to describe the relation between them using some other way? (I know the result won't be a straight line and won't be a first degree equation).
Because how do you measure a "good enough" equation? The formulas we use essentially say, rewrite the variables until we have a linear relationship, then fit the data to the line, and then if need be transform back. You can skip that if you can come up with a better way of defining "good enough" that is quantitative.
Thanks for this!
Thanks rob
Why not leave the small x's and y's as they are (not take their logarithms), and try to figure out a good enough equation to describe the relation between them using some other way? (I know the result won't be a straight line and won't be a first degree equation).
Because how do you measure a "good enough" equation? The formulas we use essentially say, rewrite the variables until we have a linear relationship, then fit the data to the line, and then if need be transform back. You can skip that if you can come up with a better way of defining "good enough" that is quantitative.
@@robertcruikshank4501 thanks for the reply
Why not use your calculator