Bimodality Coefficient Calculation with Matlab

The present code is a Matlab function that provides calculation of the Warren Sarle’s bimodality coefficient (BC) of a data, which is in relation with the data skewness and kurtosis. BC has a range of 0 to 1 where values greater than 5/9 (~0.555 – the value for the uniform distribution) indicate bimodal or multimodal data distributions. Consequently, the BC could be used as a test for bimodality of the data. The function computes:
- the bimodality flag (whether the data are bimodal/multimodal or not);
- the bimodality coefficient itself.

An example is given in order to clarify the usage of the function. For convenience, the input and output arguments are given in the beginning of the function.

The code is based on the theory described in:

[1] R. Pfister, K. Schwarz, M. Janczyk, R. Dale, J. Freeman. Good things peak in pairs: a note on the bimodality coefficient. Frontiers in Psychology, Vol. 4, Art. 700, Oct. 2013.