The 4PL model
y = D + (A − D) ÷ (1 + (x ÷ C)B)
A is the response at zero concentration, D the response at very high concentration, C the inflection point (the EC50 or IC50 for a symmetric curve) and B the slope. Most ELISA standard curves follow this shape; 5PL adds an asymmetry term for curves that aren't symmetric.
What you get
- Fitted parameters with standard errors and 95% confidence intervals, R² and residuals.
- Back-calculated concentrations for each sample, with replicate CVs and a dilution factor applied.
- Samples outside the standards are flagged as above or below range rather than extrapolated.
- Models: 4PL, 5PL, linear, quadratic, cubic, exponential, logarithmic, power and Michaelis–Menten, with optional 1/Y² weighting.
- For 4PL and 5PL, the top or bottom can be fixed, for example at your blank, when the standards don't reach a plateau. Confidence intervals and degrees of freedom allow for the fixed values.
Accuracy
The fitting is compared with SciPy on 14 datasets covering every model. Parameters agree to better than 0.0001%. How we check our calculators.