search

datadesk / census-data-aggregator

Combine U.S. census data responsibly
MIT License
42 stars 9 forks source link

negative values from numpy.random.normal #24

Open sastoudt opened 5 years ago

sastoudt commented 5 years ago

For smaller values or with large margins of error, the numpy.random.normal in approximate_mean may return a negative number which won't make sense in context. We should probably just use max(0, simulated_value) instead.

sastoudt commented 5 years ago

addressed in https://github.com/datadesk/census-data-aggregator/pull/20