## Labor Market Dynamics: A Hidden Markov Approach

_IMF Working Papers, December 20, 2019_

## Source details

**Canonical URL:** [Labor Market Dynamics: A Hidden Markov Approach](https://www.imf.org/en/publications/wp/issues/2019/12/20/labor-market-dynamics-a-hidden-markov-approach-48798)

## Other formats

- [Markdown version](/en/publications/wp/issues/2019/12/20/labor-market-dynamics-a-hidden-markov-approach-48798/index.md)
- [Structured JSON version](/en/publications/wp/issues/2019/12/20/labor-market-dynamics-a-hidden-markov-approach-48798/index.json)
- [Bundle manifest](/en/publications/wp/issues/2019/12/20/labor-market-dynamics-a-hidden-markov-approach-48798/bundle-manifest.json)

## Bibliographic details
- Authors: Ippei Shibata
- Published: December 20, 2019
- Series: IMF Working Papers
- DOI: https://doi.org/10.5089/9781513519265.001

---

### Overview
- Title: Labor Market Dynamics: A Hidden Markov Approach
- Author: Ippei Shibata
- Date: December 20, 2019
- Series: Working Paper No. 2019/282
- Core proposition: Introduces a hidden state Markov model (HMM) that incorporates workers’ unobserved labor market attachment into the analysis of labor market dynamics.

### Methodology
- Model innovation:
  - Proposes a hidden state Markov model (HMM) that allows workers with the same observed labor force status to have different history-dependent transition probabilities.
  - Contrasts with the typical assumption in previous literature that a worker’s observed labor force status follows a first-order Markov process.
- Empirical fit:
  - The estimated HMM generates labor market transition probabilities that match those observed in the data.
  - The HMM improves the fit of the empirical transition probabilities by a factor of 30 compared with the extended first-order Markov model (FOM).

### Key findings and analytical results
- Transition dynamics:
  - HMM captures history-dependent transition probabilities among workers sharing the same observed labor force status.
  - First-order Markov model (FOM) and its many-state extensions cannot match the observed transition probabilities in the data as the HMM does.
- Quantitative improvements:
  - Fit improvement: HMM improves the fit of empirical transition probabilities by a factor of 30 relative to the extended FOM.

### Applications and empirical uses
- The paper applies the HMM to:
  - Calculate the long-run consequences of separation from stable employment.
  - Study evolutions of employment stability across different demographic groups over the past several decades.
  - Compare the dynamics of labor market flows during the Great Recession to those during the 1981 recession.
  - Highlight the importance of looking beyond distributions of current labor force status.

### Subject classification and keywords
- Subject: Employment, Employment rate, Labor, Labor force, Labor markets, Unemployment
- Keywords: attachment state, Employment, Employment rate, employment stability, Labor force, labor force history, labor force status, labor market attachment state, labor market dynamics, labor market transition, Labor markets, transition dynamics, transition probability, Unemployment, unemployment state, unobserved state, WP

---

## Content in this bundle

- **Working Paper**
  - [Working Paper (Markdown version)](/-/media/files/publications/wp/2019/wpiea2019282-print-pdf.pdf.md){rel="alternate" type="text/markdown"}
  - [Working Paper (PDF)](/-/media/files/publications/wp/2019/wpiea2019282-print-pdf.pdf){rel="external" type="application/pdf"}

---

_Source: https://www.imf.org/en/publications/wp/issues/2019/12/20/labor-market-dynamics-a-hidden-markov-approach-48798_