This page contains step-by-step tutorials showing how to use ndCurveMaster for nonlinear regression, curve fitting, model validation, multicollinearity elimination, data-driven equation discovery, and related tasks.
The examples below present practical workflows based on real datasets and illustrate how regression models can be built, improved, validated, and interpreted in a transparent analytical form.
Learn how to build, validate, and improve a nonlinear regression model using a data-driven workflow,
including overfitting detection and model optimisation.
Read the nonlinear regression tutorial
Discover how to remove proportional bias and validate a regression model using the Bland–Altman test
on an independent medical dataset in ndCurveMaster.
Read the Bland–Altman tutorial
Learn how to detect multicollinearity using VIF and correlation analysis, combine correlated predictors,
and improve regression model reliability in ndCurveMaster.
Read the multicollinearity elimination tutorial
See how to move from a simple polynomial fit to a more accurate nonlinear equation and improve curve fitting
results step by step in ndCurveMaster.
Read the curve fitting tutorial
Learn how to fit a function with three input variables, compare a polynomial model with an optimized nonlinear model,
and achieve much higher accuracy in ndCurveMaster.
Read the 4D curve fitting tutorial
Explore how ndCurveMaster can discover physical relationships directly from data using examples based on acceleration,
equivalent resistance, and Coulomb’s law.
Read the physical equation discovery tutorial
Learn how to estimate the constants of the general solution of a differential equation from measurement data
using a beam deflection example in ndCurveMaster.
Read the differential equation constants tutorial