Excel 2003 is not displaying the proper equation if you insert a trendline to
data and click on the "display equation" check box. If you use the equation
to generate "y" from the exact "x" values that you began with, you get a
completely different curve than the original trendline displayed on the
graph. For example: Use the "log" function in a worksheet to plot y=log(x)
from x=1 to 100, plot the data, and fit a 2nd order polynomial to this data,
clicking on "display equation". It won't be a good fit, but this is beside
the point. Use the equation Excel generated to re-plot the y=f(x) values x=1
to 100. The data does not fall on the trend line. Why is this?

----------------
This post is a suggestion for Microsoft, and Microsoft responds to the
suggestions with the most votes. To vote for this suggestion, click the "I
Agree" button in the message pane. If you do not see the button, follow this
link to open the suggestion in the Microsoft Web-based Newsreader and then
click "I Agree" in the message pane.

http://www.microsoft.com/office/comm...excel.charting

I should add that I've tried to increase the significant digits in the
equation to 30 in scientific, but Excel doesn't appear to be responding to
this. I still get an equation that looks like "y = -0.0002x2 + 0.0373x +
0.4745"

"wsander2" wrote:

Excel 2003 is not displaying the proper equation if you insert a trendline to
data and click on the "display equation" check box. If you use the equation
to generate "y" from the exact "x" values that you began with, you get a
completely different curve than the original trendline displayed on the
graph. For example: Use the "log" function in a worksheet to plot y=log(x)
from x=1 to 100, plot the data, and fit a 2nd order polynomial to this data,
clicking on "display equation". It won't be a good fit, but this is beside
the point. Use the equation Excel generated to re-plot the y=f(x) values x=1
to 100. The data does not fall on the trend line. Why is this?

----------------
This post is a suggestion for Microsoft, and Microsoft responds to the
suggestions with the most votes. To vote for this suggestion, click the "I
Agree" button in the message pane. If you do not see the button, follow this
link to open the suggestion in the Microsoft Web-based Newsreader and then
click "I Agree" in the message pane.

http://www.microsoft.com/office/comm...excel.charting

When I reformat that trendline equation to show more figures, I get
y = -1.94230739776658E-04*x^2 + 3.20631890271028E-02*x + 6.17688698712797E-01
in both Excel 2003 and Excel 2000.

Jerry

"wsander2" wrote:

I should add that I've tried to increase the significant digits in the
equation to 30 in scientific, but Excel doesn't appear to be responding to
this. I still get an equation that looks like "y = -0.0002x2 + 0.0373x +
0.4745"

"wsander2" wrote:

Excel 2003 is not displaying the proper equation if you insert a trendline to
data and click on the "display equation" check box. If you use the equation
to generate "y" from the exact "x" values that you began with, you get a
completely different curve than the original trendline displayed on the
graph. For example: Use the "log" function in a worksheet to plot y=log(x)
from x=1 to 100, plot the data, and fit a 2nd order polynomial to this data,
clicking on "display equation". It won't be a good fit, but this is beside
the point. Use the equation Excel generated to re-plot the y=f(x) values x=1
to 100. The data does not fall on the trend line. Why is this?

----------------
This post is a suggestion for Microsoft, and Microsoft responds to the
suggestions with the most votes. To vote for this suggestion, click the "I
Agree" button in the message pane. If you do not see the button, follow this
link to open the suggestion in the Microsoft Web-based Newsreader and then
click "I Agree" in the message pane.

http://www.microsoft.com/office/comm...excel.charting