Fitting correlated data

C. Michael
1994 Physical Review D, Particles and fields  
We discuss fitting correlated data - with the example of hadron mass spectroscopy in mind. The main conclusion is that the method of minimising correlated $\chi^2$ is unreliable if the data sample is too small.
doi:10.1103/physrevd.49.2616 pmid:10017248 fatcat:cakuotx24zc5vp6pmdu2i7yu7i