hidimstat.desparsified_group_lasso_pvalue

hidimstat.desparsified_group_lasso_pvalue(beta_hat, theta_hat, precision_diagonal, test='chi2')

Compute p-values for the desparsified group Lasso estimator using chi-squared or F tests

Parameters:

beta_hatndarray, shape (n_features, n_times)

Estimated parameter matrix from desparsified group Lasso.

theta_hatndarray, shape (n_times, n_times)

Estimated precision matrix (inverse covariance).

precision_diagonalndarray, shape (n_features,)

Diagonal elements of the precision matrix.

test{‘chi2’, ‘F’}, default=’chi2’

Statistical test for computing p-values: - ‘chi2’: Chi-squared test (recommended for large samples) - ‘F’: F-test

Returns:

pvalndarray, shape (n_features,)

Raw p-values, numerically accurate for positive effects (p-values close to 0).

pval_corrndarray, shape (n_features,)

P-values corrected for multiple testing using Benjamini-Hochberg procedure.

one_minus_pvalndarray, shape (n_features,)

1 - p-values, numerically accurate for negative effects (p-values close to 1).

one_minus_pval_corrndarray, shape (n_features,)

1 - corrected p-values.

Notes

The Chi-squared test assumes asymptotic normality while the F-test is preferable for small sample sizes. P-values are computed based on score statistics from the estimated coefficients and precision matrix.