TY - RPRT T1 - Earnings Inequality and Mobility Trends in the United States: Nationally Representative Estimates from Longitudinally Linked Employer-Employee Data Y1 - 2017 A1 - Abowd, John M. A1 - McKinney, Kevin L. A1 - Zhao, Nellie AB - Earnings Inequality and Mobility Trends in the United States: Nationally Representative Estimates from Longitudinally Linked Employer-Employee Data Abowd, John M.; McKinney, Kevin L.; Zhao, Nellie Using earnings data from the U.S. Census Bureau, this paper analyzes the role of the employer in explaining the rise in earnings inequality in the United States. We first establish a consistent frame of analysis appropriate for administrative data used to study earnings inequality. We show that the trends in earnings inequality in the administrative data from the Longitudinal Employer-Household Dynamics Program are inconsistent with other data sources when we do not correct for the presence of misused SSNs. After this correction to the worker frame, we analyze how the earnings distribution has changed in the last decade. We present a decomposition of the year-to-year changes in the earnings distribution from 2004-2013. Even when simplifying these flows to movements between the bottom 20%, the middle 60% and the top 20% of the earnings distribution, about 20.5 million workers undergo a transition each year. Another 19.9 million move between employment and nonemployment. To understand the role of the firm in these transitions, we estimate a model for log earnings with additive fixed worker and firm effects using all jobs held by eligible workers from 2004-2013. We construct a composite log earnings firm component across all jobs for a worker in a given year and a non-firm component. We also construct a skill-type index. We show that, while the difference between working at a low- or middle-paying firm are relatively small, the gains from working at a top-paying firm are large. Specifically, the benefits of working for a high-paying firm are not only realized today, through higher earnings paid to the worker, but also persist through an increase in the probability of upward mobility. High-paying firms facilitate moving workers to the top of the earnings distribution and keeping them there. PB - Cornell University UR - http://hdl.handle.net/1813/52609 ER - TY - RPRT T1 - Modeling Endogenous Mobility in Earnings Determination Y1 - 2016 A1 - Abowd, John M. A1 - McKinney, Kevin L. A1 - Schmutte, Ian M. AB - Modeling Endogenous Mobility in Earnings Determination Abowd, John M.; McKinney, Kevin L.; Schmutte, Ian M. We evaluate the bias from endogenous job mobility in fixed-effects estimates of worker- and firm-specific earnings heterogeneity using longitudinally linked employer-employee data from the LEHD infrastructure file system of the U.S. Census Bureau. First, we propose two new residual diagnostic tests of the assumption that mobility is exogenous to unmodeled determinants of earnings. Both tests reject exogenous mobility. We relax the exogenous mobility assumptions by modeling the evolution of the matched data as an evolving bipartite graph using a Bayesian latent class framework. Our results suggest that endogenous mobility biases estimated firm effects toward zero. To assess validity, we match our estimates of the wage components to out-of-sample estimates of revenue per worker. The corrected estimates attribute much more of the variation in revenue per worker to variation in match quality and worker quality than the uncorrected estimates. Replication code can be found at DOI: http://doi.org/10.5281/zenodo.zenodo.376600 and our Github repository endogenous-mobility-replication . PB - Cornell University UR - http://hdl.handle.net/1813/40306 ER - TY - JOUR T1 - Noise infusion as a confidentiality protection measure for graph-based statistics JF - Statistical Journal of the International Association for Official Statistics Y1 - 2016 A1 - Abowd, John M. A1 - McKinney, Kevin L. AB - We use the bipartite graph representation of longitudinally linked employer-employee data, and the associated projections onto the employer and employee nodes, respectively, to characterize the set of potential statistical summaries that the trusted custodian might produce. We consider noise infusion as the primary confidentiality protection method. We show that a relatively straightforward extension of the dynamic noise-infusion method used in the U.S. Census Bureau's Quarterly Workforce Indicators can be adapted to provide the same confidentiality guarantees for the graph-based statistics: all inputs have been modified by a minimum percentage deviation (i.e., no actual respondent data are used) and, as the number of entities contributing to a particular statistic increases, the accuracy of that statistic approaches the unprotected value. Our method also ensures that the protected statistics will be identical in all releases based on the same inputs. VL - 32 UR - http://content.iospress.com/articles/statistical-journal-of-the-iaos/sji958 IS - 1 ER - TY - RPRT T1 - Modeling Endogenous Mobility in Wage Determination Y1 - 2015 A1 - Abowd, John M. A1 - McKinney, Kevin L. A1 - Schmutte, Ian M. AB - Modeling Endogenous Mobility in Wage Determination Abowd, John M.; McKinney, Kevin L.; Schmutte, Ian M. We evaluate the bias from endogenous job mobility in fixed-effects estimates of worker- and firm-specific earnings heterogeneity using longitudinally linked employer-employee data from the LEHD infrastructure file system of the U.S. Census Bureau. First, we propose two new residual diagnostic tests of the assumption that mobility is exogenous to unmodeled determinants of earnings. Both tests reject exogenous mobility. We relax the exogenous mobility assumptions by modeling the evolution of the matched data as an evolving bipartite graph using a Bayesian latent class framework. Our results suggest that endogenous mobility biases estimated firm effects toward zero. To assess validity, we match our estimates of the wage components to out-of-sample estimates of revenue per worker. The corrected estimates attribute much more of the variation in revenue per worker to variation in match quality and worker quality than the uncorrected estimates. PB - Cornell University UR - http://hdl.handle.net/1813/40306 ER - TY - RPRT T1 - Modeling Endogenous Mobility in Wage Determination Y1 - 2015 A1 - Abowd, John M. A1 - McKinney, Kevin L. A1 - Schmutte, Ian M. AB - Modeling Endogenous Mobility in Wage Determination Abowd, John M.; McKinney, Kevin L.; Schmutte, Ian M. We evaluate the bias from endogenous job mobility in fixed-effects estimates of worker- and firm-specific earnings heterogeneity using longitudinally linked employer-employee data from the LEHD infrastructure file system of the U.S. Census Bureau. First, we propose two new residual diagnostic tests of the assumption that mobility is exogenous to unmodeled determinants of earnings. Both tests reject exogenous mobility. We relax exogenous mobility by modeling the matched data as an evolving bipartite graph using a Bayesian latent-type framework. Our results suggest that allowing endogenous mobility increases the variation in earnings explained by individual heterogeneity and reduces the proportion due to employer and match effects. To assess external validity, we match our estimates of the wage components to out-ofsample estimates of revenue per worker. The mobility-bias corrected estimates attribute much more of the variation in revenue per worker to variation in match quality and worker quality than the uncorrected estimates. PB - NCRN Coordinating Office UR - http://hdl.handle.net/1813/52608 ER - TY - RPRT T1 - Noise Infusion as a Confidentiality Protection Measure for Graph-Based Statistics Y1 - 2015 A1 - Abowd, John A. A1 - McKinney, Kevin L. AB - Noise Infusion as a Confidentiality Protection Measure for Graph-Based Statistics Abowd, John A.; McKinney, Kevin L. We use the bipartite graph representation of longitudinally linked employer-employee data, and the associated projections onto the employer and employee nodes, respectively, to characterize the set of potential statistical summaries that the trusted custodian might produce. We consider noise infusion as the primary confidentiality protection method. We show that a relatively straightforward extension of the dynamic noise-infusion method used in the U.S. Census Bureau’s Quarterly Workforce Indicators can be adapted to provide the same confidentiality guarantees for the graph-based statistics: all inputs have been modified by a minimum percentage deviation (i.e., no actual respondent data are used) and, as the number of entities contributing to a particular statistic increases, the accuracy of that statistic approaches the unprotected value. Our method also ensures that the protected statistics will be identical in all releases based on the same inputs. PB - Cornell University UR - http://hdl.handle.net/1813/42338 ER -