Kurtosis

Kurtosis is a statistic to measure the tail heaviness of a data distribution. The kurtosis of an analysis domain is calculated as follows:

The summation is over all included samples i in the analysis domain,

n	is the number of samples included in the summation.
Ei	is the linear Sv of sample i (m2/m3) -  set to 0 for any sample where Ei < mSv or Ei > MSv,
En	is the observed Mean Energy of the analysis domain in linear units (m2/m3) = 10Sv/10
mSv	is the minimum integration threshold (dB re 1 m-1) at time of processing.
MSv	is the maximum integration threshold (dB re 1 m-1) at time of processing.
ESD	Standard_deviation (Standard Deviation of the Energy)

For Linear data, Ei is the sample value and En is the arithmetic mean of the included sample values in the analysis domain.

For TS, Power dB, and Unspecified dB data, Ei is the linear equivalent of the sample value and En is the arithmetic mean of those linear equivalents in the analysis domain.

For information about undefined calculations for these data types, see the Standard deviation, Skewness and Kurtosis note.

All symbols are as defined in the nomenclature developed for SHAPES algorithms.

See also

About kurtosis
School Detection module algorithms
Other region variables for schools analysis