Fitting Interface For User-Selectable Polynomial
y = a + bx + cx
2
+ dx
3
+ ...
Pulldown Menu
Text Data Editor
Fitting Target
Data Labels For Graphs
Polynomial Selection
Graph Scaling And Lin/Log Control
Graph Size
Graph Colors
Scientific Notation For Graphs
Introduction
Home
Introduction
Please select an option from the pull-down menu above.
Text data editor
Cut-and-paste text or edit data here
Convert commas to spaces (1,2,0,3 yields 1 2 0 3)
Use comma as decimal separator (1,203 = 1.203)
Remove commas from text (1,2,0,3 yields 1203)
Standard Unweighted Fitting: no weights required
Weighted Fitting: each data point requires a weight
This data is provided as an example, cut and paste as needed to model your data. All lines of text that do not begin with a number are ignored. Weighted fitting requires an additional number to be used as a weight when fitting. The site does not calculate any weights, which are used as: error = weight * (predicted - actual) You must provide any weights you wish to use. X Y 5.357 0.376 5.457 0.489 5.797 0.874 5.936 1.049 6.161 1.327 6.697 2.054 6.731 2.077 6.775 2.138 8.442 4.744 9.769 7.068 9.861 7.104
Fitting Target
Here you can select the desired fitting target.
Lowest sum of squared (SSQ) absolute error (traditional)
Lowest sum of orthogonal distance (ODR) (robust, slow)
Lowest sum of squared (SSQ) relative error (robust, slow)
Lowest sum of absolute value of absolute error (robust, slow)
Lowest sum of absolute value of relative error (robust, slow)
Lowest peak absolute value of absolute error (robust, slow)
Lowest peak absolute value of relative error (robust, slow)
Lowest AIC (robust, slow)
Lowest BIC (robust, slow)
Data labels for graphs
Here you can enter the X and Y data labels to be printed on the report graphs.
Label for first independent data (X)
Label for dependent data (Y)
Graph scaling and lin/log control
Here you can choose the scaling of the data plots.
Log plots require data values greater than zero.
X Scale
Y Scale
Autoscale +/- 1%
Autoscale +/- 2.5%
Autoscale +/- 5%
Autoscale +/- 10%
Autoscale +/- 25%
Autoscale +/- 50%
Autoscale +/- 100%
Autoscale +/- 150%
Autoscale +/- 200%
Manual Scale
Max X:
Min X:
Linear Scaling
Logarithmic Scaling
Autoscale +/- 1%
Autoscale +/- 2.5%
Autoscale +/- 5%
Autoscale +/- 10%
Autoscale +/- 25%
Autoscale +/- 50%
Autoscale +/- 100%
Autoscale +/- 150%
Autoscale +/- 200%
Manual Scale
Max Y:
Min Y:
Linear Scaling
Logarithmic Scaling
Graph size
Here you can choose the size of the report graphs. Smaller size files load quickly,
with less resolution while large files show more resolution but load more slowly.
320 x 240 (fastest)
500 x 400
640 x 480
700 x 500
800 x 600
900 x 700
1024 x 768
1280 x 1024
1600 x 1200 (slowest)
Graph colors
Here you can select various color options for the output graphs.
Graph background color
Graph text color
Graph line color
Scientific Notation
Here you can control scientific notation on the data plots.
X Control
Y Control
On
Off
Auto
On
Off
Auto
Polynomial selection
Select the highest order term for the polynomial equation.
0
1
2
3
4
5
6
7
8
The source code for the site middleware is at
the Python Equations Google Code Repository
.
Superior quality PDF file on practical curve fitting:
Fitting Models to Experimental Data
Test Data Sets
courtesy of
Mr. Ready's Online Math Classroom - Calculus
Follow site updates with Twitter at
http://twitter.com/ZunZunTweets
.