Minimum Data Points for 4PL and 5PL

3 posts / 0 new
Last post
rgm's picture
Minimum Data Points for 4PL and 5PL


I have two questions:

1. In my Elisa results, I have 4 standard calibrators and 1 negative standard (conc= 0 IU/ml).Is it possible to use 4PL or 5PL equations for only 5 data points( 5 standards)?
2. In Elisa test instruction that the company gave me, it is noted that the calibration curve should be a linear plot. But my results can be better explained by non linear curves. Am I allowed to disregard test instruction in this case?

Any help would be appreciated.

Amy Rayo
Amy Rayo's picture

1.  Did you run QCs?  And if so where on the curve do they lie?  If it's an assay you have run multiple times, 5 should be fine.  8 is more standard though.  Also, did you back calculate your calibrators and make sure they are 20% RE?  2.  Linearity depends on the type of enzyme kinetics you are dealing with and how you plot your graph. Log-Log would be linear.  Lin-Log would be sigmoidal.  

Toon Smetsers
Toon Smetsers's picture
4PL and 5PL on ELISA with 5 data point

 Yes it is possible to use 5 data points with a 4PL or 5PL fit in ELISA. You can use it free forever on  If your test instructions indicate a linear reqgression should be used, the assay is validated with a linear regression and the claims and data in the instructions for use are based on the linear regression. If your assay is an IVD assay and you are reporting patient data with it, you are bound by the instructions for use.  If your test is a research use only test you can decide for yourself what you would like to use as a fit function, however if you us a different function as stated in the package insert your performance data will also be different from the data in the IFU.