Fixed-effect regressions on network data

Jochmans, Koen; Weidner, Martin

doi:10.1920/wp.cem.2017.2617

Cited by 28 publications

(53 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mobility patterns of workers define a graph across firm classes. A measure of connectedness of a graph is the smallest non-zero eigenvalue of its normalized Laplacian, as recently studied in Jochmans and Weidner (2017). 5 We observed that the local optima of the likelihood function tended to vary substantially in terms of their connectedness, some of the solutions having types with very low connectedness.…”

Section: S21 Estimation Of Parametersmentioning

confidence: 60%

“…In Supplementary Appendix S2 we describe how we use the EM algorithm to explore the likelihood function. We also explain how we use a measure of network connectedness recently studied in Jochmans and Weidner (2017) to select our preferred estimates. 27 On the left panel of Figure 2 we plot estimates of the means of log-earnings for each firm class and each worker type.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Distributional Framework for Matched Employer Employee Data

2017

View full text Add to dashboard Cite

We propose a framework to identify and estimate earnings distributions and worker composition on matched panel data, allowing for two-sided worker-firm unobserved heterogeneity. We introduce two models: a static model that allows for nonlinear interactions between workers and firms, and a dynamic model that allows in addition for Markovian earnings dynamics and endogenous mobility. We establish identification in short panels, and develop tractable two-step estimators where firms are classified into heterogeneous classes in a first step. Applying our method to Swedish administrative data, we find that log-earnings are approximately additive in worker and firm heterogeneity, with a strong association between workers and firms, and a small relative contribution of firm heterogeneity to earnings dispersion. In addition, we document that wages have a direct effect on mobility, and that, beyond their dependence on the current firm, earnings after a job move also depend on the past firm.

show abstract

Section: S21 Estimation Of Parametersmentioning

confidence: 60%

Section: Resultsmentioning

confidence: 99%

A Distributional Framework for Matched Employer Employee Data

2017

View full text Add to dashboard Cite

show abstract

“…In addition, some local maxima have poor connectedness, in the sense that some worker types only move within a subset of firm classes, which results in unstable parameter estimates. We use the EM algorithm to explore the likelihood function, and use a measure of network connectedness recently studied in Jochmans and Weidner () to select our preferred estimates; see the Supplemental Material for details.…”

Section: Empirical Results I: Static Modelmentioning

confidence: 99%

A Distributional Framework for Matched Employer Employee Data

Lamadon

Manresa

2019

ECTA

201

173

View full text Add to dashboard Cite

We propose a framework to identify and estimate earnings distributions and worker composition on matched panel data, allowing for two‐sided worker‐firm unobserved heterogeneity and complementarities in earnings. We introduce two models: a static model that allows for nonlinear interactions between workers and firms, and a dynamic model that allows, in addition, for Markovian earnings dynamics and endogenous mobility. We show that this framework nests a number of structural models of wages and worker mobility. We establish identification in short panels, and develop tractable two‐step estimators where firms are classified in a first step. Applying our method to Swedish administrative data, we find that log‐earnings are approximately additive in worker and firm heterogeneity. Our estimates imply the presence of strong sorting patterns between workers and firms, and a small contribution of firms—net of worker composition—to earnings dispersion. In addition, we document that wages have a direct effect on mobility, and that, beyond their dependence on the current firm, earnings after a job move also depend on the previous employer.

show abstract

“…The results in Figure 3 show that grouped-fixed-effects estimators have moderate bias for 32 all parameters except for the wage coefficient in utility ρ. 38 Using both bias reduction and an iteration improves the performance of the estimator of ρ substantially. Note that, when combined with half-panel jackknife, a single iteration seems sufficient to reduce bias.…”

Section: All Workersmentioning

confidence: 99%

“…This application illustrates the potential usefulness of discrete grouped fixed-effects estimators in the presence of continuous unobserved heterogeneity. Computation of two-step esti- 38 The estimated number of groups K is around 7 on average. 39 In the counterfactual we keep the probability of being a "stayer type" constant.…”

Section: All Workersmentioning

confidence: 99%

Discretizing Unobserved Heterogeneity

2017

View full text Add to dashboard Cite

We study panel data estimators based on a discretization of unobserved heterogeneity when individual heterogeneity is not necessarily discrete in the population. We focus on two-step grouped-fixed effects estimators, where individuals are classified into groups in a first step using kmeans clustering, and the model is estimated in a second step allowing for group-specific heterogeneity. We analyze the asymptotic properties of these discrete estimators as the number of groups grows with the sample size, and we show that bias reduction techniques can improve their performance. In addition to reducing the num-ber of parameters, grouped fixed-effects methods provide effective regularization. When allowing for the presence of time-varying unobserved heterogeneity, we show they enjoy fast rates of convergence depending of the underlying dimension of heterogeneity. Finally, we document the finite sample properties of two-step grouped fixedeffects estimators in two applications: a structural dynamic discrete choice model of migration, and a model of wages with worker and firm heterogeneity.JEL codes: C23, C38.

show abstract

Fixed-effect regressions on network data

Cited by 28 publications

References 38 publications

A Distributional Framework for Matched Employer Employee Data

A Distributional Framework for Matched Employer Employee Data

A Distributional Framework for Matched Employer Employee Data

Discretizing Unobserved Heterogeneity

Contact Info

Product

Resources

About