linearmodels.iv.covariance.kernel_weight_parzen¶

linearmodels.iv.covariance.kernel_weight_parzen(bw: float, *args: int) → ndarray[source]¶

Kernel weights from a Parzen kernel

Parameters:¶

bw: float¶

Maximum lag to used in kernel

Returns:¶

Weight array ordered by lag position (maxlag + 1)

Return type:¶

numpy.ndarray

Notes

\[\begin{split}z_i & = i / (m+1) \\ w_i & = 1-6z_i^2+6z_i^3, z \leq 0.5 \\ w_i & = 2(1-z_i)^3, z > 0.5\end{split}\]