A Regression-Based Shapley Decomposition for Inequality Measures

View at Publisher

Ask AI

Bookmark

Share

Key Points

To introduce a regression-based Shapley decomposition framework for assessing and breaking down the contributions of distinct factors to overall inequality measures.
Integrated cooperative game theory principles using the Shapley value with standard econometric regression models.
Formulated mathematical attribution rules across multiple continuous and categorical explanatory covariates.
Yields an exact, additive breakdown of overall inequality metrics into individual factor contributions without leaving an unexplained residual.
Overcomes path-dependency limitations inherent to standard sequential decomposition methods by averaging marginal contributions over all possible elimination sequences.

We only have this paper's title and publication details.

Methodological analysis reveals an exact decomposition framework for inequality metrics, indicating improved factor attribution.

International audience

No takes yet. Share an insight, caveat, or question.

Fourrey (2023) studied this question.

View at Publisher

Ask AI

Bookmark

Share