statsmodels.nonparametric.kernel_density.KDEMultivariate.pdf¶

KDEMultivariate.pdf(data_predict=None)[source]¶

Evaluate the probability density function.

Parameters:¶

data_predict : array_like, optional¶

Points to evaluate at. If unspecified, the training data is used.

Returns:¶

pdf_est – Probability density function evaluated at data_predict.

Return type:¶

array_like

Notes

The probability density is given by the generalized product kernel estimator:

\[K_{h}(X_{i},X_{j}) = \prod_{s=1}^{q}h_{s}^{-1}k\left(\frac{X_{is}-X_{js}}{h_{s}}\right)\]