ICSH recommendations for the analysis of red cell, white cell and platelet size distribution curves. Methods for fitting a single reference distribution and assessing its goodness of fit. International Committee for Standardization in Haematology. ICSH Expert Panel on Cytometry

The algorithm in Figure 7 summarizes the overall approach to fitting a single reference distribution. If no statistically significant difference is found, the investigation should assess whether the power of the chi-squared test was insufficient to detect differences of practical significance. If a statistical difference is found, Appendices B and C and Figure 6 may be used to determine whether the sample size and the power have led to the detection of an effect size too small to be of importance.

Published by Clinical and laboratory haematology, 1990. The guideline itself is at the source linked here.

pubmed.ncbi.nlm.nih.gov/2081383/