Linear Regression:
The process for obtaining the best fit is frequently called the "regression". Linear regression stands for straight line fitting of data.
Linear approximations are frequently satisfactory in a broad variety of engineering applications.
If we choose a straight line for curve fitting as:
f (x) = a + bx, here a & b are coefficients to be find out. Then for "best fit", the sum S that is to be minimized will be
![2436_Linear Regression.png](https://www.expertsmind.com/CMSImages/2436_Linear%20Regression.png)
The minimum tale place when
![858_Linear Regression1.png](https://www.expertsmind.com/CMSImages/858_Linear%20Regression1.png)
These might be simplified & expressed like following
![167_Linear Regression2.png](https://www.expertsmind.com/CMSImages/167_Linear%20Regression2.png)
These two simultaneous equations might be solved to get the coefficients a and b. The resulting equation f (x) = a + bx then gives the best fit straight line to the specified data. The spread of data before regression applied might be n,
![1956_Linear Regression3.png](https://www.expertsmind.com/CMSImages/1956_Linear%20Regression3.png)
Here yavg might be average or mean of the specified data. The extent of development because of curve fitting is specified by the expression
![386_Linear Regression4.png](https://www.expertsmind.com/CMSImages/386_Linear%20Regression4.png)
Here r is the correlation coefficient.
It might be noted down that r contain a maximum value of 1.0. Its value shall be greater for good correlation!