floatcsep.extras.negative_binomial_number_test(gridded_forecast, observed_catalog, variance)[source]

Computes “negative binomial N-Test” on a gridded forecast.

Computes Number (N) test for Observed and Forecasts. Both data sets are expected to be in terms of event counts. We find the Total number of events in Observed Catalog and Forecasted Catalogs. Which are then employed to compute the probablities of (i) At least no. of events (delta 1) (ii) At most no. of events (delta 2) assuming the negative binomial distribution.

  • gridded_forecast – Forecast of a Model (Gridded) (Numpy Array) A forecast has to be in terms of Average Number of Events in Each Bin It can be anything greater than zero

  • observed_catalog – Observed (Gridded) seismicity (Numpy Array): An Observation has to be Number of Events in Each Bin It has to be a either zero or positive integer only (No Floating Point)

  • variance – Variance parameter of negative binomial distribution obtained from historical catalog.


(delta_1, delta_2)

Return type:

out (tuple)