﻿ PRINCIPLES OF REGRESSION
GraphPad Curve Fitting Guide

# PRINCIPLES OF REGRESSION

Many scientists fit curves more often than the use any other statistical technique. Yet few statistical texts really explain the principles of curve fitting. This Guide provides a concise introduction to fitting curves, especially nonlinear regression.

The first step is to be clear on what your goal is:

If your goal is to fit a model to your data in order to obtain best-fit values of the parameters, and want to learn the principles first, then read this principles section before trying to fit curves.

If you already understand the principles of nonlinear regression, and want to see how to fit curves with Prism, jump right to the tutorials.

If your goal is to simply fit a smooth curve in order to interpolate values from the curve, there is no need to learn much theory. Jump right to an explanation of interpolation with Prism.

If your goal is to create a spline (a curve that goes through every data point) or a lowess curve ( shows the general trend with a curve that can be quite jagged), you can jump right to the instructions for that analysis.