Dresden 2020 – scientific programme

The DPG Spring Meeting in Dresden had to be cancelled! Read more ...

Parts | Days | Selection | Search | Updates | Downloads | Help

BP: Fachverband Biologische Physik

BP 19: Poster VII

BP 19.28: Poster

Tuesday, March 17, 2020, 14:00–16:00, P2/3OG

Pitfalls in statistical data analysis — •Thomas John and Christian Wagner — Experimentalphysik, Universität Saarland

During your studies, you learned various ways of evaluating and displaying data. We would like to introduce some further statistical evaluation methods. After the presentation, you may no longer generate histograms with bars and you will never again try to fit a Gaussian curve to an empirical probability distribution. Even if both methods are intuitively clear, it delivers less precise results as more indirect methods. As keywords, we would mention: kernel density estimators and fitting to empirical cumulative distribution functions.

[1] D. W. Scott, Multivariate Density Estimation: Theory, Practice and Visualization, Wiley Series in Probability and Statistics 2015.