stats.stationarity.augmented_dickey_fuller

stats.stationarity.augmented_dickey_fuller(y, *, autolag='AIC')

Run an Augmented Dickey-Fuller test on a time series.

Returns a structured pd.Series instead of printing — callers decide how to display the result.

Parameters

Name	Type	Description	Default
y	pd.Series	Series to test. Must be a non-empty pandas Series without missing values (validated via `check_y`).	required
autolag	str	Lag-selection criterion forwarded to `statsmodels.tsa.stattools.adfuller`. Defaults to `"AIC"`.	`'AIC'`

Returns

Name	Type	Description
	pd.Series	`pd.Series` with the index
	pd.Series	["statistic", "p_value", "n_lags", "n_obs", "critical_1%", \| \| \| [pd](`pandas`).[Series](`pandas.Series`) \| "critical_5%", "critical_10%"].

Raises

Name	Type	Description
	TypeError	If `y` is not a pandas Series.
	ValueError	If `y` contains missing values.

Examples

import numpy as np
import pandas as pd

from spotforecast2_safe.stats.stationarity import (
    augmented_dickey_fuller,
)

rng = np.random.default_rng(0)
y = pd.Series(rng.standard_normal(500))
out = augmented_dickey_fuller(y)
print(out["p_value"] < 0.05)

True