You need to think about how you did the experiment, and decide whether some of the parameters should be fixed. Remember that nonlinear regression programs have no "common sense". For example, you might fix the bottom plateau of a sigmoid curve or exponential decay to zero. It is often helpful to define constants when you have only a few data points.
Instead, you may fix one or more of the parameters to constant values. When performing nonlinear regression, you don't have to fit each parameter in the equation. Decide whether to constrain any parameters Initial values matter more when your data have a lot of scatter or your model has many variables. You'll get the same best-fit curve no matter what initial values you use, unless the initial values are extremely far from correct. When fitting a simple model to clean data, it won't matter much if the initial values are fairly far from the correct values. Once you have a better feel for how the parameters influence the curve, you might find it easier to estimate initial values. Change the variables one at a time, and see how they influence the shape of the curve. If you are having problems estimating initial values, set aside your data and simulate curves using the model. You'll find it easy to estimate initial values if you have looked at a graph of the data, understand the model, and understand the meaning of all the parameters in the equation. The Initial Values tab of the Nonlinear regression dialog lets you review, and override, the computed initial values. Once you define these rules, Prism will compute appropriate initial values based on the range of your data. For example the initial value of one parameter may be twice the maximum Y value in the data, while the initial value of another parameter may equal the average of the highest and lowest X values. If you enter your own equation, you can also enter rules for initial values. GraphPad Prism provides initial values automatically if you use a built-in equation. It then adjusts these initial values to improve the fit. The program must start with estimated values for each variable that are in the right "ball park" - say within a factor of five of the actual value. Nonlinear regression is an iterative procedure. Why a computer program cannot pick a model for you. You must, therefore, choose a model or enter a new model.
Nonlinear regression fits a model to your data. Or click Analyze and select from the analyze dialog. If you have replicate Y values at each X value, format the table for entry of replicates.įrom an XY table or graph, click the shortcut button to fit a model with nonlinear regression.