Scipy kolmogorov smirnov test for evaluating the fitting of a non-normal distribution - Printable Version +- Python Forum (https://python-forum.io) +-- Forum: Python Coding (https://python-forum.io/forum-7.html) +--- Forum: General Coding Help (https://python-forum.io/forum-8.html) +--- Thread: Scipy kolmogorov smirnov test for evaluating the fitting of a non-normal distribution (/thread-27107.html) |
Scipy kolmogorov smirnov test for evaluating the fitting of a non-normal distribution - mcva - May-26-2020 Hi thank you in advance for reading this Can Scipy kolmogorov smirnov (KS) test be used for evaluating the fitting of a non-normal distribution like the Exponnorm, to a continuous variable? My observed data is a series of 2083 observed daily flow records. I´m using the following code to test the fitting: test=kstest(x,'exponnorm', {15.423611244139217, 5.930740266809032, 1.799877032067283}),and these are the results: KstestResult(statistic=0.8600795890927582, pvalue=0.0) Considering the critical value for the KS test = 0.0289 the null hypothesis would be rejected. Nevertheless when I look at the probability plot, the fitting seems ok. I´m doing something wrong? Thank you so much |