FitR2

Description: This function returns the coefficient of determination (i.e. r2) for a linear curve fit. This number gives a measure of how accurate the curve fit is.

Returns: Numeric

Usage: Script or Steady State

Format: FitR2(XarrayElem, YarrayElem, N)

Parameters: XArrayElem { array element } { required } { no default: }

Any array element giving the starting point in the array of X coordinates of the input data set. The subscript for the array may be any numeric expression. Unless specified, the lowest dimension of a multidimensional array is used.

YArrayElem { array element } { required } { no default: }

Any array element giving the starting point in the array of Y coordinates of the input data set. The subscript for the array may be any numeric expression. Unless specified, the lowest dimension of a multidimensional array is used.

N { numeric } { required } { no default: }

Any numeric expression giving the number of data points to use from the arrays given by the first two parameters. If N extends past the upper bound of the lowest array dimension, this computation will "wrap-around" and resume at element 0, until N elements have been processed.

Comments: This function returns a number indicating how close a fit the data are to a line. If an element of either array is invalid, then that X-Y pair is not included in the computation. If the result is 0, there is no linear relationship at all between the array of X values and the array of Y values. If the result is 1, the fit is perfect. The result may be any value in the range of 0 to 1.

This function can be used in conjunction with the other linear regression functions.

Example:

Assume that 2 arrays exist such that x = {0, 1, 2, 3} and y = {1, 3, 5, 7 }, and both arrays' subscripts start at 0

determination = FitR2(x[0] { Starting X element },

y[0] { Starting Y element },

4 { Number of elements to process });

The value of determination will be set to 1 (a perfect fit).