📝 Original Paper Info
- Title: Recovering Latent Variables by Matching
- ArXiv ID: 1912.13081
- Date: 2020-01-01
- Authors: Manuel Arellano, Stephane Bonhomme
📝 Abstract
We propose an optimal-transport-based matching method to nonparametrically estimate linear models with independent latent variables. The method consists in generating pseudo-observations from the latent variables, so that the Euclidean distance between the model's predictions and their matched counterparts in the data is minimized. We show that our nonparametric estimator is consistent, and we document that it performs well in simulated data. We apply this method to study the cyclicality of permanent and transitory income shocks in the Panel Study of Income Dynamics. We find that the dispersion of income shocks is approximately acyclical, whereas the skewness of permanent shocks is procyclical. By comparison, we find that the dispersion and skewness of shocks to hourly wages vary little with the business cycle.
💡 Summary & Analysis
This paper proposes an optimal transport-based matching method to nonparametrically estimate linear models with independent latent variables. The main challenge addressed is the difficulty in directly estimating latent variables, which can affect a model's predictive power, especially when analyzing income shocks' characteristics during economic cycles. By generating pseudo-observations from these latent variables and minimizing the Euclidean distance between the model's predictions and matched counterparts in real data, the method ensures more accurate estimations. The study demonstrates that this approach is consistent and performs well on simulated datasets. It applies this technique to analyze the cyclicality of permanent and transitory income shocks using the Panel Study of Income Dynamics (PSID). Key findings include discovering that the dispersion of income shocks is nearly acyclical, whereas the skewness of permanent shocks tends to be procyclical. In contrast, shocks to hourly wages show little variation with the business cycle. This research enhances our understanding of how economic cycles impact various types of income and wage shocks, offering a robust framework for more accurate modeling in economic analysis.
📄 Full Paper Content (ArXiv Source)
[^1]: CEMFI, Madrid.
A Note of Gratitude
The copyright of this content belongs to the respective researchers. We deeply appreciate their hard work and contribution to the advancement of human civilization.