Dealing with non-uniform distributions, and implement other SA methods.

[willfinnigan]

Currently only the Sobol Sensitivity Analysis is implemented through SALib. Implement other methods?

SALib only takes uniform distributions, so using other distributions is a bit of a problem?

If we have a normal distribution can we just approximate this as a uniform distribution for use in SALib by taking the 5th and 95th percentile as the lower and upper bounds?

[willfinnigan]

Interesting approach for sampling from log-uniform

https://waterprogramming.wordpress.com/2014/02/11/extensions-of-salib-for-more-complex-sensitivity-analyses/

"One approach is instead to uniformly sample the exponent of the parameter. For example, if your parameter value ranges from [0.001, 1000], sample from [-3, 3]. Then transform the value back into real space after you read it into your model (and of course, before you do any calculations!) This way you can still use uniform sampling while ensuring fair representation in your parameter space."

[willfinnigan]

This has been looked at but I don't think included in SALib
SALib/SALib#192