statsmodels.stats.diagnostic.linear_harvey_collier¶
-
statsmodels.stats.diagnostic.
linear_harvey_collier
(res, order_by=None)[source]¶ Harvey Collier test for linearity
The Null hypothesis is that the regression is correctly modeled as linear.
- Parameters
res : RegressionResults
A results instance from a linear regression.
order_by : array_like, default None
Integer array specifying the order of the residuals. If not provided, the order of the residuals is not changed. If provided, must have the same number of observations as the endogenous variable.
- Returns
tvalue : float
The test statistic, based on ttest_1sample.
pvalue : float
The pvalue of the test.
Notes
This test is a t-test that the mean of the recursive ols residuals is zero. Calculating the recursive residuals might take some time for large samples.