Sharp EL-9600 manual Other Regressions

Chapter nine

OTHER REGRESSIONS

AND MODEL OF “BEST FIT”

Introducing the Topic

In this chapter, you and your students will learn how to use the Sharp graphing calculator to find several regression equations for a set of data points and then determine the model of "best fit." A regression equation is a model of the relationship between the dependent variable Y and the independent variable X. Other regression models include y = ax 2 + bx + c (quadratic), y = ax 3 + bx 2 + cx + d (cubic), y = ax4 + bx 3 + cx 2 + dx + e (quartic), y = a + b ln x (natural logarithm), y = a + b log x (common logarithm), y = a*bx (exponential), y = a*ebX (natural exponential), y = a + bx-1(inverse), and Y = a*Xb (power). The a, b, c, d and e are calculated for each model in order to find the best-fitting curve (minimized error).

A third value, r 2, is calculated for each regression and is a measure of how well the equation fits the data points, and it will range from 0 to 1. If r 2 = 1, then the equation intersects all the data points, and the model is said to have perfect fit. Values of r 2 close to 1 are said to reflect a good fit, and values close to 0 are said to reflect a poor fit.

44Other Regressions and Model of “Best Fit”/STATISTICS USING THE SHARP EL-9600