-
Finding Needles in Haystacks: Multiple-Imputation Record Linkage Using Machine Learning
November 2021
Working Paper Number:
CES-21-35
This paper considers the problem of record linkage between a household-level survey and an establishment-level frame in the absence of unique identifiers. Linkage between frames in this setting is challenging because the distribution of employment across establishments is highly skewed. To address these difficulties, this paper develops a probabilistic record linkage methodology that combines machine learning (ML) with multiple imputation (MI). This ML-MI methodology is applied to link survey respondents in the Health and Retirement Study to their workplaces in the Census Business Register. The linked data reveal new evidence that non-sampling errors in household survey data are correlated with respondents' workplace characteristics.
View Full
Paper PDF
-
Heavy Tailed, but not Zipf: Firm and Establishment Size in the U.S.
July 2021
Working Paper Number:
CES-21-15
Heavy tails play an important role in modern macroeconomics and international economics.
Previous work often assumes a Pareto distribution for firm size, typically with a shape parameter approaching Zipf's law. This convenient approximation has dramatic consequences for the importance of large firms in the economy. But we show that a lognormal distribution, or better yet, a convolution of a lognormal and a non-Zipf Pareto distribution, provides a better description of the U.S. economy, using confidential Census Bureau data. These findings hold even far in the upper tail and suggest heterogeneous firm models should more systematically explore deviations from Zipf's law.
View Full
Paper PDF
-
Business Applications as a Leading Economic Indicator?
May 2021
Working Paper Number:
CES-21-09R
How are applications to start new businesses related to aggregate economic activity? This paper explores the properties of three monthly business application series from the U.S. Census Bureau's Business Formation Statistics as economic indicators: all business applications, business applications that are relatively likely to turn into new employer businesses ('likely employers'), and the residual series -- business applications that have a relatively low rate of becoming employers ('likely non-employers'). Growth in applications for likely employers significantly leads total nonfarm employment growth and has a strong positive correlation with it. Furthermore, growth in applications for likely employers leads growth in most of the monthly Principal Federal Economic Indicators (PFEIs). Motivated by our findings, we estimate a dynamic factor model (DFM) to forecast nonfarm employment growth over a 12-month period using the PFEIs and the likely employers series. The latter improves the model's forecast, especially in the years following the turning points of the Great Recession and the COVID-19 pandemic. Overall, applications for likely employers are a strong leading indicator of monthly PFEIs and aggregate economic activity, whereas applications for likely non-employers provide early information about changes in increasingly prevalent self-employment activity in the U.S. economy.
View Full
Paper PDF
-
The Children of HOPE VI Demolitions: National Evidence on Labor Market Outcomes
November 2020
Working Paper Number:
CES-20-39
We combine national administrative data on earnings and participation in subsidized housing to study how the demolition of 160 public housing projects'funded by the HOPE VI program'affected the adult labor market outcomes for 18,500 children. Our empirical strategy compares children exposed to the program to children drawn from thousands of non-demolished projects, adjusting for observable differences using a flexible estimator that combines features of matching and regression. We find that children who resided in HOPE VI projects earn 14% more at age 26 relative to children in comparable non-HOPE VI projects. These earnings gains are strongest for demolitions in large cities, particularly in neighborhoods with higher pre-demolition poverty rates and lower pre-demolition job accessibility. There is no evidence that the labor market gains are driven by improvements in household or neighborhood environments that promote human capital development in children. Rather, subsequent improvements in job accessibility represent a likely pathway for the results.
View Full
Paper PDF
-
The Impact of 2010 Decennial Census Hiring on the Unemployment Rate
June 2020
Working Paper Number:
CES-20-19
The decennial census is the largest peacetime operation of the U.S. federal government. The Census Bureau hires hundreds of thousands of temporary workers to conduct the decennial census. The magnitude of this temporary workforce influences the national employment situation when enumeration efforts ramp up and when they recede. The impact of decennial census hiring on the headline number of payroll jobs added each month is well established, but previous work has not established how decennial census hiring affects the headline unemployment rate. We link the 2010 Decennial Applicant Personnel and Payroll System data to the 2010 American Community Survey to answer this question. We find that the large hiring surge in May 2010 came mostly from people already employed (40 percent) or from people who were unemployed (33 percent). We estimate that the workers hired for Census 2010 lowered the May 2010 unemployment rate by one-tenth of a percentage point relative to the counterfactual. This one-tenth of a percentage point is within the standard error for the official unemployment rate, and BLS press releases would denote a change in the unemployment rate of 0.1% or less as 'unchanged.' We also estimate that relative to the counterfactual, the more gradual changes in decennial census employment influenced the unemployment rate by less than one-tenth of a percentage point in every other month during 2010.
View Full
Paper PDF
-
The Energy Efficiency Gap and Energy Price Responsiveness in Food Processing
June 2020
Working Paper Number:
CES-20-18
This paper estimates stochastic frontier energy demand functions with non-public, plant-level data from the U.S. Census Bureau to measure the energy efficiency gap and energy price elasticities in the food processing industry. The estimates are for electricity and fuel use in 4 food processing sectors, based on the disaggregation of this industry used by the National Energy Modeling System Industrial Demand Module. The estimated demand functions control for plant inputs and output, energy prices, and other observables including 6-digit NAICS industry designations. Own price elasticities range from 0.6 to -0.9 with little evidence of fuel/electricity substitution. The magnitude of the efficiency estimates is sensitive to the assumptions but consistently reveal that few plants achieve 100% efficiency. Defining a 'practical level of energy efficiency' as the 95th percentile of the efficiency distributions and averaging across all the models result in a ~20% efficiency gap. However, most of the potential reductions in energy use from closing this efficiency gap are from plants that are 'low hanging fruit'; 13% of the 20% potential reduction in the efficiency gap can be obtained by bringing the lower half of the efficiency distribution up to just the median level of observed performance. New plants do exhibit higher energy efficiency than existing plants which is statistically significant, but the difference is small for most of the industry; ranging from a low of 0.4% to a high of 5.7%.
View Full
Paper PDF
-
Misallocation or Mismeasurement?
February 2020
Working Paper Number:
CES-20-07
The ratio of revenue to inputs differs greatly across plants within countries such as the U.S. and India. Such gaps may reflect misallocation which hinders aggregate productivity. But differences in measured average products need not reflect differences in true marginal products. We propose a way to estimate the gaps in true marginal products in the presence of measurement error. Our method exploits how revenue growth is less sensitive to input growth when a plant's average products are overstated by measurement error. For Indian manufacturing from 1985'2013, our correction lowers potential gains from reallocation by 20%. For the U.S. the effect is even more dramatic, reducing potential gains by 60% and eliminating 2/3 of a severe downward trend in allocative efficiency over 1978'2013.
View Full
Paper PDF
-
Nonemployer Statistics by Demographics (NES-D):
Exploring Longitudinal Consistency and Sub-national Estimates
December 2019
Working Paper Number:
CES-19-34
Until recently, the quinquennial Survey of Business Owners (SBO) was the only source of information for U.S. employer and nonemployer businesses by owner demographic characteristics such as race, ethnicity, sex and veteran status. Now, however, the Nonemployer Statistics by Demographics series (NES-D) will replace the SBO's nonemployer component with reliable, and more frequent (annual) business demographic estimates with no additional respondent burden, and at lower imputation rates and costs. NES-D is not a survey; rather, it exploits existing administrative and census records to assign demographic characteristics to the universe of approximately 25 million (as of 2016) nonemployer businesses.
Although only in the second year of its research phase, NES-D is rapidly moving towards production, with a planned prototype or experimental version release of 2017 nonemployer data in 2020, followed by annual releases of the series. After the first year of research, we released a working paper (Luque et al., 2019) that assessed the viability of estimating nonemployer demographics exclusively with administrative records (AR) and census data. That paper used one year of data (2015) to produce preliminary tabulations of business counts at the national level. This year we expand that research in multiple ways by: i) examining the longitudinal consistency of administrative and census records coverage, and of our AR-based demographics estimates, ii) evaluating further coverage from additional data sources, iii) exploring estimates at the sub-national level, iv) exploring estimates by industrial sector, v) examining demographics estimates of business receipts as well as of counts, and vi) implementing imputation of missing demographic values.
Our current results are consistent with the main findings in Luque et al. (2019), and show that high coverage and demographic assignment rates are not the exception, but the norm. Specifically, we find that AR coverage rates are high and stable over time for each of the three years we examine, 2014-2016. We are able to identify owners for approximately 99 percent of nonemployer businesses (excluding C-corporations), 92 to 93 percent of identified nonemployer owners have no missing demographics, and only about 1 percent are missing three or more demographic characteristics in each of the three years. We also find that our demographics estimates are stable over time, with expected small annual changes that are consistent with underlying population trends in the U.S.. Due to data limitations, these results do not include C-corporations, which represent only 2 percent of nonemployer businesses and 4 percent of receipts.
Without added respondent burden and at lower imputation rates and costs, NES-D will provide high-quality business demographics estimates at a higher frequency (annual vs. every 5 years) than the SBO.
View Full
Paper PDF
-
What Do Establishments Do When Wages Increase?
Evidence from Minimum Wages in the United States
November 2019
Working Paper Number:
CES-19-31
I investigate how establishments adjust their production plans on various margins when wage rates increase. Exploiting state-by-year variation in minimum wage, I analyze U.S. manufacturing plants' responses over a 23-year period. Using instrumental variable method and Census Microdata, I find that when the hourly wage of production workers increases by one percent, manufacturing plants reduce the total hours worked by production workers by 0.7 percent and increase capital expenditures on machinery and equipment by 2.7 percent. The reduction in total hours worked by production workers is driven by intensive-margin changes. The estimated elasticity of substitution between capital and labor is 0.85. Following the wage increases, no statistically significant changes emerge in revenue, materials or total factor productivity. Additionally, I nd that when wage rates increase, establishments are more likely to exit the market. Finally, I provide evidence that when the minimum wage increases the wages of some of the establishments in a firm, the firm also increases the wages for its other establishments.
View Full
Paper PDF
-
Addressing Data Gaps:
Four New Lines of Inquiry in the 2017 Economic Census
September 2019
Working Paper Number:
CES-19-28
We describe four new lines of inquiry added to the 2017 Economic Census regarding (i) retail health clinics, (ii) management practices in health care services, (iii) self-service in retail and service industries, and (iv) water use in manufacturing and mining industries. These were proposed by economists from the U.S. Census Bureau's Center for Economic Studies in order to fill data gaps in current Census Bureau products concerning the U.S. economy. The new content addresses such issues as the rise in importance of health care and its complexity, the adoption of automation technologies, and the importance of measuring water, a critical input to many manufacturing and mining industries.
View Full
Paper PDF
