def bootstrap_from_outcomes(
data, outcome, bootstrap_outcomes, ci_method="percentile", alpha=0.05, n_cores=1
):
"""Set up results table containing mean, standard deviation and confidence interval
for each estimated parameter.
Args:
data (pandas.DataFrame): original dataset.
outcome (callable): function of the data calculating statistic of interest.
Needs to return a pandas Series.
bootstrap_outcomes (pandas.DataFrame): DataFrame of bootstrap_outcomes in the
bootstrap samples.
ci_method (str): method of choice for confidence interval computation.
n_cores (int): number of jobs for parallelization.
alpha (float): significance level of choice.
Returns:
results (pandas.DataFrame): table of results.
"""
check_inputs(data=data, ci_method=ci_method, alpha=alpha)
summary = pd.DataFrame(bootstrap_outcomes.mean(axis=0), columns=["mean"])
summary["std"] = bootstrap_outcomes.std(axis=0)
cis = compute_ci(data, outcome, bootstrap_outcomes, ci_method, alpha, n_cores)
summary["lower_ci"] = cis["lower_ci"]
summary["upper_ci"] = cis["upper_ci"]
cov = bootstrap_outcomes.cov()
out = {"summary": summary, "cov": cov, "outcomes": bootstrap_outcomes}
return out
def test_bca_ci(setup, expected):
bca_ci = compute_ci(setup["df"], g, setup["estimates"], ci_method="bca")
aaae(bca_ci, expected["bca_ci"])
def test_percentile_ci(setup, expected):
percentile_ci = compute_ci(setup["df"],
g,
setup["estimates"],
ci_method="percentile")
aaae(percentile_ci, expected["percentile_ci"])
def test_normal_ci(setup, expected):
normal_ci = compute_ci(setup["df"],
g,
setup["estimates"],
ci_method="normal")
aaae(normal_ci, expected["normal_ci"])
def test_t_ci(setup, expected):
t_ci = compute_ci(setup["df"], g, setup["estimates"], ci_method="t")
aaae(t_ci, expected["t_ci"])