climpred.bootstrap.bootstrap_hindcast¶

climpred.bootstrap.bootstrap_hindcast(hind, hist, reference, metric='pearson_r', comparison='e2r', dim='init', sig=95, bootstrap=500, pers_sig=None, **metric_kwargs)[source]¶

Bootstrap compute with replacement. Wrapper of: py:func:bootstrap_compute for hindcasts.

Parameters:

hind (xr.Dataset) – prediction ensemble.
reference (xr.Dataset) – reference simulation.
hist (xr.Dataset) – historical/uninitialized simulation.
metric (str) – metric. Defaults to ‘pearson_r’.
comparison (str) – comparison. Defaults to ‘e2r’.
dim (str) – dimension to apply metric over. default: ‘init’
sig (int) – Significance level for uninitialized and initialized skill. Defaults to 95.
pers_sig (int) – Significance level for persistence skill confidence levels. Defaults to sig.
bootstrap (int) – number of resampling iterations (bootstrap with replacement). Defaults to 500.
metric_kwargs (**) – additional keywords to be passed to metric (see the arguments required for a given metric in Metrics).

Returns:

(xr.Dataset): bootstrapped results

init_ci (xr.Dataset): confidence levels of init_skill
uninit_ci (xr.Dataset): confidence levels of uninit_skill
p_uninit_over_init (xr.Dataset): p value of the hypothesis

that the difference of skill between the initialized and uninitialized simulations is smaller or equal to zero based on bootstrapping with replacement. Defaults to None.
pers_ci (xr.Dataset): confidence levels of pers_skill
p_pers_over_init (xr.Dataset): p value of the hypothesis

that the difference of skill between the initialized and persistence simulations is smaller or equal to zero based on bootstrapping with replacement. Defaults to None.

Return type:

results

Reference:

Goddard, L., A. Kumar, A. Solomon, D. Smith, G. Boer, P. Gonzalez, V. Kharin, et al. “A Verification Framework for Interannual-to-Decadal Predictions Experiments.” Climate Dynamics 40, no. 1–2 (January 1, 2013): 245–72. https://doi.org/10/f4jjvf.