labor-economics

What problem does it solve?

Labor economics analysis often requires estimating wage equations, correcting sample selection bias, and decomposing wage gaps between groups, as well as understanding how covariates shift the entire wage distribution rather than only mean outcomes.

Core Features & Use Cases

• Mincer wage equation estimation: Estimate returns to education and experience using a log-wage specification with experience and experience-squared.
• Heckman two-step selection correction: Correct wage regressions when wages are only observed for workers who participate in the labor market, using a probit selection model and an Inverse Mills Ratio.
• Oaxaca-Blinder decomposition: Decompose mean log-wage gaps between two groups into explained (endowments) and unexplained (returns/coefficients) components.
• Unconditional quantile regression (RIF regression): Estimate covariate effects on the unconditional wage distribution across quantiles (e.g., 10th to 90th), supporting policy questions about distributional impacts.

Use Case: Analyze the education and wage relationship while comparing gender wage gaps and quantile effects, correcting for non-random labor force participation using an exclusion restriction such as children under 6 or nonlabor income.

Quick Start

Use the labor-economics skill to estimate a Mincer wage equation with Heckman selection correction, then run Oaxaca-Blinder decomposition and RIF unconditional quantile regression for the same dataset.