Basic Statistics: Reciprocal Variable Better Fit?

[shakystew]

Hello,

I have some data that I am looking into correlation factors (Pearson). Let's say I have two data sets: X and Y. I have Graph X vs. Y then graph 1/X vs. Y. The reciprocal (1/X) yields a more linear relationship. Why does this occur?

Thanks in advance!

 

[mfb]

The reciprocal (1/X) yields a more linear relationship. Why does this occur?

Maybe your data has roughly Y~1/X?
Why do you expect a linear relationship at all?