Indirect Inference Structural Estimation
Expert TheoryReview
Estimating general equilibrium search models directly via maximum likelihood is often intractable due to unobserved heterogeneity, complex dynamic interactions, and multi-stage empirical experimental designs.
Picture this
Imagine trying to map the unseen internal gears of a complex clock. Instead of opening it, you run experiments—shaking it at different speeds and measuring how the hands move. Then, you build a computer model of clock gears and adjust the virtual gears until the computer clock behaves identical to the real clock across all physical tests.
What the evidence says
The structural parameters matched the reduced-form empirical moments (treatment exit rate, control exit rate, regional comparison exit rate, and vacancy response curves), validating structural policy simulation counterfactuals.
- Who was studied
- Administrative baseline and post-treatment tracking data of N = 40,403 Danish workers combined with 14-county aggregate vacancy series.
- How
- Auxiliary statistical models (reduced-form hazard models and difference-in-differences regressions) are estimated on both empirical experimental data and simulated model data to minimize the distance vector between empirical and simulated parameter estimates.
What to do
Calibrate structural general equilibrium parameters by matching reduced-form experimental treatment effect moments using indirect inference.
From the source
"To estimate the structural model parameters, we use the method of indirect inference. The main idea is to use an auxiliary statistical model to capture features of the data, and to estimate the parameters of the structural model by matching the auxiliary parameters estimated from real data with those estimated from simulated data."
816b5187-9076-4043-aba7-184043b2e524-Estimating Equilibrium Effects of Job Search Assistance.pdf