Wednesday, August 4, 2010

least squares regression line

Let us learn about least squares regression line


Regression is the measure of the average relationship between two or more variables in terms of the original units of the data. This can be represented by an equation of a straight line which can be obtained by the method of least squares. The equations are of two forms as y on x and x on y. To obtain them we use the following normal equatons.

(i) Regression line y on x: It is given by y = hx + k.

Their normal equations are:

Σy = hΣx + nk ……………… (1)

Σxy = hΣx 2 + kΣx …………. (2)

By solving (1) and (2), we arrive at the required equation y = hx + k
(ii) Regression line x on y: It is given by x = hy + k.

Their normal equations are:

Σx = hΣy + nk ……….. (1)

Σxy = hΣy 2 + kΣy ………… (2)

By solving (1) and (2), we arrive at the required equations x = hy + k

In our next blog we shall learn about converting 1 meter in feet

I hope the above explanation was useful.Keep reading and leave your comments.



No comments:

Post a Comment