Free Curve Fitting & Statistics
Curve Fitting & Statistics fits 4-parameter dose–response (IC50/EC50), exponential, Michaelis–Menten, power, logarithmic, Gaussian, polynomial and custom models to x/y data, reporting parameters with standard errors, 95% confidence intervals and R². It also runs Welch, Student, paired and one-sample t-tests and one-way ANOVA, and exports charts as PNG or SVG.
- Models:
- 4PL, exponential, polynomial, custom
- Tests:
- t-tests and one-way ANOVA
- Fit output:
- SE, 95% CI and R²
- Price:
- Free
- Runs:
- Locally, in your browser
- Uploads:
- None: files never leave your device
- Account:
- Not needed
Quick answers
How do I get an IC50?
Choose “Dose–response 4PL”, paste concentrations and responses, and read EC50 in the results (shown as IC50 for a falling curve). The log x axis is turned on automatically.
Is my data uploaded?
No. Fitting and statistics run entirely in your browser; nothing leaves your device.
Processed on your device: your files are never uploaded. How it works
Network activity in this tab
What this page has requested since you opened the site in this tab. An upload is any request that sends data: POST, PUT, PATCH or a request with a body.
No uploads: nothing has been sent from this page.
No network requests yet.
To see every request, open your browser's developer tools (Network tab).
How to use the Curve Fitting & Statistics
- Paste your x/y data from a spreadsheet (a header row is optional) and pick a model, or write your own formula.
- Read the fitted parameters with standard errors and 95% confidence intervals, R² and the curve over your points; use a log x axis for dose–response data.
- Switch to Statistics to compare groups with t-tests or a one-way ANOVA.
- Download the chart as PNG or SVG, the fitted curve as CSV, or copy the results table.
Credits & open source
Our own code plus open-source libraries. Thank you to the people who make these projects.
- ml-levenberg-marquardtNon-linear least-squares curve fitting (Levenberg–Marquardt). © ml.js contributors · MIT
- jStatStatistical distributions and tests (t, F, chi-square, normal). © jStat contributors · MIT
Web platform APIs used: Canvas 2D, Clipboard API, File API.
Full license texts: third-party notices · all credits
Frequently asked questions
Which t-test should I use?
Welch's two-sample test unless your groups are paired (the same subjects measured twice), in which case use the paired test. Welch's test does not assume equal variances.
Can I fit my own equation?
Yes. Choose “Custom formula” and type it with x and single-letter parameters, for example a*exp(-b*x)+c. Giving rough initial values helps the fit converge.
How accurate are the results?
Parameters come from standard least squares, and the t-test and ANOVA p-values match R. Standard errors are asymptotic estimates, as in most fitting software.