Regression analysis curve fitting

In general, regression analysis of reference designs can be linear, i.e. we draw a straight line through the cloud of points. The line can be represented by the equation:

y = a ■ x + b where the coefficients a and b have to be determined so as to give a 'best fit' through the cloud of points.

Linear least square curve fitting means that we determine the coefficients a and b such that the sum of the squares of the deviations of the points from the regression line is at its minimum.

For n points, having coordinates (xm,ym), m = 1, 2,..., n, this sum, S, is:

The values for a and b that minimise S are those that satisfy the conditions dS/da = 0 and dS/db = 0. Differentiating (8.6) with respect to a and b yields (after rearranging terms and substitution):

Best Investment Tips and Ideas

Best Investment Tips and Ideas

The dynamics of investing can be very emotional and stressful if not properly managed. When you are aware of what is all involved you give yourself the power to avoid those situations or at least manage them effectively. That will make your investments more exciting, rewarding, and enjoyable. Those positive factors will only lead to greater success in all that achieve with investments and life.

Get My Free Ebook

Post a comment