statsmodels.regression.mixed_linear_model.MixedLM.get_scale

MixedLM.get_scale(fe_params, cov_re, vcomp)[source]

Returns the estimated error variance based on given estimates of the slopes and random effects covariance matrix.

Parameters:
  • fe_params (array-like) – The regression slope estimates
  • cov_re (2d array-like) – Estimate of the random effects covariance matrix
  • vcomp (array-like) – Estimate of the variance components
Returns:

scale – The estimated error variance.

Return type:

float