Fitting a truncated normal (Gaussian) distribution

How to fit a truncated distribution

Version 1.2.0.0 (2.2 KB)
733 Downloads
(5)
8 Feb 2018

You are now following this Submission

Matlab does not allow to say that a distribution which we fit to a dataset is truncated.
In case of a Gaussian distribution, Matlab just calculates the mean and sigma and uses them as the paramters of a pdf, but this does not work if the distribution is cutted from one side, e.g. when you don't have measurements less than some detection limit. Then fitted distribution will be shifted.
Here I give an small example how to perform fitting in this case.

Cite As

Alex Ryabov (2026). Fitting a truncated normal (Gaussian) distribution (https://uk.mathworks.com/matlabcentral/fileexchange/64040-fitting-a-truncated-normal-gaussian-distribution), MATLAB Central File Exchange. Retrieved .

General Information

MATLAB Release Compatibility

  • Compatible with any release

Platform Compatibility

  • Windows
  • macOS
  • Linux
Open in new tab
Version Published Release Notes
1.2.0.0

Now the function can fit distributions truncated either on the left or on the right or both sides
updated the figure
1.1.0.0

I converted script to a function
Script was converted to a function
1.0.0.0

--