Koen Van de Moortel

• Master of Science
• writer, programmer, private teacher & photographer at independent math & physics tutor

There are tons of books about measuring, regression analysis and mathematical modeling, but my focus is quite different. I will teach you: • The world cannot be described by linear models alone, absolutely not! There is a lot of beautiful other functions available! • Measurement errors should not be neglected. • Using common sense can make your...

Book about measuring and modeling, using ordinary and multidirectional regression analysis, for students, teachers, researchers, engineers...

FittingKVdm 1.14 has been released! There are many software programs that do regression analysis (curve fitting), BUT only this one makes optimal use of the symmetry whenever dependent and independent variables can be switched! This will definitely improve your scientific modeling or calibration work! And in most cases it will estimate good initial...

(European) shoe sizes of adults versus their height (126 men and 242 women, mostly from Belgium and Holland, Feb. 2023) - an educational example of my regression software "FittingKVdm".

Software manual version 1.9, with more models and examples.

Two methods for finding the "best" curve fitting through a set of data points are evaluated here: "multidirectional" and "ordinary" least squares regression (MDLS and OLS). The same artificial datasets with several amplitudes of generated noise were fed to both algorithms and the results were compared.

This real life example shows why Multidirectional regression is better than the classical method (OLS): it treats the so-called independent and dependent variables equally.

Does a person unconsciously improve his psychomotor while performing a simple task like throwing a pebble? Apparently he/she does, at least with our test person. The hypothesis was tested with 3 different methods: comparing averages, Kendall's tau, and regression.

Regression analysis software manual with many real life examples from various sciences.

The so-called 'least squares regression' for mathematical modeling is a widely used technique. It's so common that one might think nothing could be improved to the algorithm anymore. But it can. By minimizing the squares of the differences between measured and predicted values not only in the vertical, but also in the horizontal direction. I call t...

The article shows an improvement for the well-known least squares regression analysis is possible in the case of invertible functions.

For non-linear regression, often the logarithms of the variables are taken, to reduce the problem to a linear regression. With some examples, I explain you why this is not such a good idea.