Show Tag: hartigans-dip-statistic

Select Other Tags

The Hartigans' Dip Statistic measures unimodality in a sample: Specifically, it measures the greatest difference between the empirical cumulative distribution function and that unimodal cumulative distribution function which minimizes that greatest difference.

Freeman and Dale discuss three measures for detecting bimodality in an observed probability distribution:

  • The bimodality coefficient (BC),
  • Hartigan's dip statistic (HDS), and
  • Akaike's information criterion between one-component and two-component distribution models (AID).

According to Freeman and Dale, Hartigan's dip statistic is more robust against skew than either the bimodality coefficent and Akaike's information criterion.

In Freeman and Dale's simulations, Hartigan's dip statistic was the most sensitive in detecting bimodality.

In Freeman and Dale's simulations, Hartigan's dip statistic was strongly influenced by proportion between modes.

Pfister et al. recommend using Hartigan's dip statistic and the bimodality coefficient plus visual inspection to detect bimodality.