GraphPad Curve Fitting Guide

How standard errors are computed

How standard errors are computed

Previous topic Next topic No expanding text in this topic  

How standard errors are computed

Previous topic Next topic JavaScript is required for expanding text JavaScript is required for the print function Mail us feedback on this topic!  

Prism uses a standard method to compute the standard error and confidence interval for each parameter fit with nonlinear regression.

Each parameter's standard error is computed using this equation:

  SE(Pi) = sqrt[ (SS/DF) * Cov(i,i) ]

where:

 Pi : i-th adjustable(non-constant) parameter
 SS : sum of squared residuals
 DF : degrees of freedom (the number of data points minus number of parameters fit by regression)
 Cov(i,i) : i-th diagonal element of covariance matrix
 sqrt() : square root