Databases Reference
In-Depth Information
Overall plot title
12
10
8
Y
Predicted Y
6
4
y = 1.032
∗
x
+ −
0.292
2
R
2
= 0.958
0
0
5
10
15
X axis label
FIGURE 4.30
Graph and generated linear fit data set.
Notice that the graph contains both the actual data (blue line) and the linearly fitted prediction
(red straight line). Immediately adjacent to the graph is an equidistant 50-point data set generated
by using the linearly fitted equation. The equation and the (r
2
) Value are placed on the graph, as
well as labels for the axes and a title. Most importantly, notice if the application is run more than
once; unique Worksheet and chart names are generated to hold the most recently fitted the data
sets and accompanying plots.
4.10
CREATING A POLYNOMIAL REGRESSION TOOL
USING THE VBA ANALYSIS TOOLPAK
Linear treatment of data is often preferable because of its simplicity. A linear regression is, in fact,
simply the best straight line that can be drawn through a set of plotted points. Nonlinear data are
often treated as linear data for modeling purposes just because it is so much easier to do so.
However, the sharpness and frequency of curves a plot has in it will be factors that limit if a linear
regression will provide a reasonably accurate model of the data set.
