本文共 1979 字，大约阅读时间需要 6 分钟。

是一个Python模块，提供了大量统计模型的类和函数。主要功能有：

1. regression: Generalized least squares (including weighted least squares and least squares with autoregressive errors), ordinary least squares.
2. glm: Generalized linear models with support for all of the one-parameter exponential family distributions.
   discrete choice models: Poisson, probit, logit, multinomial logit
3. rlm: Robust linear models with support for several M-estimators.
4. tsa: Time series analysis models, including ARMA, AR, VAR
5. nonparametric : (Univariate) kernel density estimators
6. datasets: Datasets to be distributed and used for examples and in testing.
7. PyDTA: Tools for reading Stata .dta files into numpy arrays.
8. stats: a wide range of statistical tests

• statsmodels.tsa.stattools.adfuller()

statsmodels.tsa.stattools.adfuller(x, maxlag=None, regression='c', autolag='AIC', store=False, regresults=False)

迪基-福勒检验Augmented Dickey-Fuller(ADF) Test

• 参数详解

1. x (array_like*,* 1d) 数据序列

2. maxlag (int) – Maximum lag which is included in test, default 12*(nobs/100)^{1/4}

3. regression ${}^{\prime }{c}^{\prime }{,}^{\prime }c{t}^{\prime }{,}^{\prime }ct{t}^{\prime }{,}^{\prime }n{c}^{\prime }$

   Constant and trend order to include in regression

   • ’c’ : constant only (default)
   • ’ct’ : constant and trend
   • ’ctt’ : constant, and linear and quadratic trend
   • ’nc’ : no constant, no trend

4. autolag ${}^{\prime }AI{C}^{\prime }{,}^{\prime }BI{C}^{\prime }{,}^{\prime }t-sta{t}^{\prime },None$

   • if None, then maxlag lags are used
   • if ‘AIC’ (default) or ‘BIC’, then the number of lags is chosen to minimize the corresponding information criterion
   • ’t-stat’ based choice of maxlag. Starts with maxlag and drops a lag until the t-statistic on the last lag length is significant using a 5%-sized test

5. store (bool) – If True, then a result instance is returned additionally to the adf statistic. Default is False

6. regresults (bool*,* optional) – If True, the full regression results are returned. Default is False