Please enable JavaScript to view this site.

This guide is for an old version of Prism. Browse the latest version or update Prism

Regression requires at least as many data points as parameters. So if you fit a dose-response model with four parameters (Bottom, Top, logEC50, and HillSlope), you must have four or more points or Prism will simply report "too few points".

Having as many points as parameters is the bare minimum. Prism will try to fit the model, and will report a perfect fit, and so not be able to report standard errors or confidence intervals. If there are only a few more points that parameters, Prism is likely to end up with an ambiguous or not converged fit.

© 1995-2019 GraphPad Software, LLC. All rights reserved.