Download citation
Download citation
link to html
In order to detect and graphically visualize the absence or presence of systematic errors in fit data, conditional probabilities are employed to analyze the statistical independence or dependence of fit residuals. This concept is completely general and applicable to all scientific fields in which model parameters are fitted to experimental data. The applications presented in this work refer to published charge-density data.

Supporting information

pdf

Portable Document Format (PDF) file https://doi.org/10.1107/S2053273314012984/eo5030sup1.pdf
BayCoN plots for all data sets, probability density histograms and normal probability plots for the artificial data sets 24-30, BayCoN plots (zeta, s.u.) for data sets 1-30 and table of chi^2 values and meta residual values for sets 1-29


Follow Acta Cryst. A
Sign up for e-alerts
Follow Acta Cryst. on Twitter
Follow us on facebook
Sign up for RSS feeds