If the coefficients of a simple regression line, B 0 and B 1 , are the same then why are the regression lines of y on x and x on y different given the condition r 2 &lt; 1. I have tried all the manipulation and graphical analysis I can but can't seem to see why this is happening.

Question

If the coefficients of a simple regression line,       B    0   and       B    1  , are the same then why are the regression lines of   y on   x and   x on   y different given the condition       r    2    &amp;lt;  1. I have tried all the manipulation and graphical analysis I can but can&#039;t seem to see why this is happening.

Lana Schwartz · Accepted Answer

In one you are trying to write a formula for   y in terms of   x. The error in the fit is the vertical distance from the data to the regression line.In the second case the error is the horizontal distance from the data to the regression line.Minimizing the sum of vertical errors is not the same as minimizing the sum of horizontal errors. In fact the discrepancy depends on       r    2    −  1.

Yesenia Obrien · Accepted Answer

To save effort, let&#039;s assume the means of the original data   xs and   ys are both   0, that their standard deviations are       σ    x   and       σ    y   are positive, and that the covariance       σ          x      y       is positive; the correlation coefficient   r  =                    σ                  x          y                                      σ          x                          σ          y                     will therefore also be positive though not more than   1.Then one possible line for the graph between the points is             y              σ        y              =            x              σ        x            , i.e.   y  =                    σ        y                    σ        x              x. You could easily end up with something close to this drawing by hand. If the correlation coefficient was   r  =  1 then all the points would lie on this line.But regressing   y on   x will not give you this result for   r  &amp;lt;  1, as it is trying to minimise the sum of squares of the vertical residuals, and it will do this by giving   y  =                    σ                  x          y                            σ        x        2              x, i.e.   y  =  r                    σ        y                    σ        x              x, reducing the slope.Meanwhile regressing   x on   y will give you a different result for   r  &amp;lt;  1, as it is trying to minimise the sum of squares of the horizontal residuals, and it will do this by giving   x  =                    σ                  x          y                            σ        y        2              y, i.e.   y  =            1      r                          σ        y                    σ        x              x and increasing the slope.One lesson to draw from this is that a lower correlation will increase the difference between regressing   y on   x and regressing   x on   y.

If the coefficients of a simple regression line, B 0 </msub> and B

Answered question

Answer & Explanation

New Questions in Inferential Statistics