xdem.spatialstats.two_step_standardization

xdem.spatialstats.two_step_standardization#

xdem.spatialstats.two_step_standardization(dvalues, list_var, unscaled_error_fun, spread_statistic=<function nmad>, fac_spread_outliers=7)[source]#

Standardize the proxy differenced values using the modelled heteroscedasticity, re-scaled to the spread statistic, and generate the final standardization function.

Parameters:

  • dvalues (NDArray[floating[Any]]) – Proxy values as array of size (N,) (i.e., differenced values where signal should be zero such as elevation differences on stable terrain)

  • list_var (list[NDArray[floating[Any]]]) – List of size (L) of explanatory variables array of size (N,)

  • unscaled_error_fun (Callable[[tuple[ArrayLike, ...]], NDArray[floating[Any]]]) – Function of the spread with explanatory variables not yet re-scaled

  • spread_statistic (Callable[[NDArray[floating[Any]]], floating[Any]]) – Statistic to be computed for the spread; defaults to nmad

  • fac_spread_outliers (float | None) – Exclude outliers outside this spread after standardizing; pass None to ignore.

Return type:

tuple[NDArray[floating[Any]], Callable[[tuple[ArrayLike, ...]], NDArray[floating[Any]]]]

Returns:

Standardized values array of size (N,), Function to destandardize