search

pierreroudier / clhs

A R implementation of the conditioned Latin Hypercube Sampling method
12 stars 9 forks source link

clhs throws an error when `sd` of a variable is 0 #2

Open dylanbeaudette opened 8 years ago

dylanbeaudette commented 8 years ago

This doesn't happen very often, but can when integer data are sampled and all values are equal.

dylanbeaudette commented 6 years ago

Is this an issue for the underlying Metropolis-Hastings algorithm or something else? Perhaps a flag for removing low-variability variables at run-time, so that you get something close to what is requested without throwing an error?