curvefit.com. Guide to nonlinear regression.Try our software free for 30 days.StatMate leads you step by step through power and sample size calculations.InStat is a less cumbersome alternative to typical heavy-duty statistical programs. With InStat, even a statistical novice can analyze data in just a few minutes.Prism is a powerful combination of basic biostatistics, curve fitting and scientific graphing in one comprehensive program.GraphPad Software. Data analysis and biostatistics resources.


spa

Table of contents
Intro to regression
Nonlinear regression
Curve fitting with Prism
Interpreting the results
Comparing two curves
Distributions of best-fit values
Radioligand binding
Saturation binding
Competitive binding

Kinetics of binding
Dose-response curves
Enzyme kinetics
Standard curves


s

Introduction
How to fit
Interpolating
Replicate unknowns
Troubleshooting
More information
Search curvefit.com


curvefit.com was created by GraphPad Software, Inc. Send comments or questions to the author of these pages, Dr. Harvey Motulsky, president of GraphPad Software.

In April 2003, GraphPad released Prism 4 and published Fitting Models to Biological Data using Linear and Nonlinear Regression. This book includes all the information that comprises curvefit.com, and much more. You can read this book as a pdf file.
Problems with standard curves

Reading unknown values from a linear regression line is completely straightforward. Reading unknown values from a curve is subject to the following potential problems:

•   Prism can only read unknowns off the standard curve within the range of the standard curve. If you enter an unknown value that is larger than the highest standard or smaller than the lowest standard, Prism will not try to determine the concentration unless you fit the standard curve with linear regression. You should interpret these extrapolations cautiously. With nonlinear regression, Prism only will perform standard curve calculations within the limits that the curve is defined. But you can extend the curve in both directions, to include lower and higher X values. Do this from the Output options dialog - press Output from the nonlinear regression parameters dialog.
•   If you calculate X from Y, beware of a possible ambiguity. It is possible that two or more points on the curve have identical Y values but different X values. In this situation, Prism will report the lowest of the X values within the range of the standard curve, and will not warn you that other answers exist.
•   You will get more accurate results if you define the curve with more line segments. Prism defines a curve as a large number of points. To find unknown values, Prism linearly interpolates between the two points on either side of the unknown value. If you define the curve with more line segments, the interpolation will be more accurate. To increase the number of line segments, click Output from the nonlinear regression parameters dialog.


All contents copyright © 1999 by GraphPad Software, Inc. All rights reserved.