confint_2group_diff
calculate_weighted_delta
def calculate_weighted_delta(
bootstrap_dist_var, differences
):
Compute the weighted deltas.
calculate_bootstraps_var
def calculate_bootstraps_var(
bootstraps
):
Call self as a function.
calculate_group_var
def calculate_group_var(
control_var, control_N, test_var, test_N
):
Call self as a function.
compute_interval_limits
def compute_interval_limits(
bias, acceleration, n_boots, ci:int=95
):
Returns the indexes of the interval limits for a given bootstrap.
Supply the bias, acceleration factor, and number of bootstraps.
compute_meandiff_bias_correction
def compute_meandiff_bias_correction(
bootstraps, # An numerical iterable, comprising bootstrap resamples of the effect size.
effsize, # The effect size for the original sample.
): # The bias correction value for the given bootstraps
and effect size.
Computes the bias correction required for the BCa method of confidence interval construction.
compute_delta2_bootstrapped_diff
def compute_delta2_bootstrapped_diff(
x1:np.ndarray, # Control group 1
x2:np.ndarray, # Test group 1
x3:np.ndarray, # Control group 2
x4:np.ndarray, # Test group 2
is_paired:str=None, resamples:int=5000, random_seed:int=12345, proportional:bool=False
)->tuple:
Bootstraps the effect size deltas’ g or proportional delta-delta
delta2_bootstrap_loop
def delta2_bootstrap_loop(
x1, x2, x3, x4, resamples, pooled_sd, rng_seed, is_paired, proportional:bool=False
):
Compute bootstrapped differences for delta-delta, handling both regular and proportional data
compute_bootstrapped_diff
def compute_bootstrapped_diff(
x0, x1, is_paired, effect_size, resamples:int=5000, random_seed:int=12345
):
Bootstraps the effect_size for 2 groups.
bootstrap_indices
def bootstrap_indices(
is_paired, x0_len, x1_len, resamples,
random_seed, # parallelization must be turned off for random number generation
):
Call self as a function.
compute_meandiff_jackknife
def compute_meandiff_jackknife(
x0, x1, is_paired, effect_size
):
Given two arrays, returns the jackknife for their effect size.
create_repeated_indexes
def create_repeated_indexes(
data
):
Convenience function. Given an array-like with length N, returns a generator that yields N indexes [0, 1, …, N].
/opt/hostedtoolcache/Python/3.12.13/x64/lib/python3.12/site-packages/fastcore/docscrape.py:259: UserWarning: Unknown section Keywords
else: warn(msg)create_jackknife_indexes
def create_jackknife_indexes(
data
):
Given an array-like, creates a jackknife bootstrap.
For a given set of data Y, the jackknife bootstrap sample J[i] is defined as the data set Y with the ith data point deleted.