-
EXPANDING THE ROLE OF SYNTHETIC DATA AT THE U.S. CENSUS BUREAU
February 2014
Working Paper Number:
CES-14-10
National Statistical offices (NSOs) create official statistics from data collected from survey respondents, government administrative records and other sources. The raw source data is usually considered to be confidential. In the case of the U.S. Census Bureau, confidentiality of survey and administrative records microdata is mandated by statute, and this mandate to protect confidentiality is often at odds with the needs of users to extract as much information from the data as possible. Traditional disclosure protection techniques result in official data products that do not fully utilize the information content of the underlying microdata. Typically, these products take the form of simple aggregate tabulations. In a few cases anonymized public- use micro samples are made available, but these face a growing risk of re-identification by the increasing amounts of information about individuals and firms available in the public domain. One approach for overcoming these risks is to release products based on synthetic data where values are simulated from statistical models designed to mimic the (joint) distributions of the underlying microdata. We discuss re- cent Census Bureau work to develop and deploy such products. We discuss the benefits and challenges involved with extending the scope of synthetic data products in official statistics.
View Full
Paper PDF
-
Financial Frictions and Investment Dynamics in Multi-Plant Firms
October 2013
Working Paper Number:
CES-13-56
Using confidential Census data on U.S. manufacturing plants, we document that most of the dispersion in investment rates across plants occurs within rms instead of across firms. Between- firm dispersion is almost acyclical, but within- rm dispersion is strongly procyclical. To investigate the role of rms in the allocation of capital in the economy, we build a multi-plant model of the firm with frictions at both levels of aggregation. We show that external nancing constraints at the level of the rm can have important implications for plant-level investment dynamics. Finally, we present empirical evidence supporting the predictions of the model.
View Full
Paper PDF
-
Spatial Organization of Firms: Internal and External Agglomeration Economies and Location Choices Through the Value Chain
September 2012
Working Paper Number:
CES-12-33
We explore the impact of geographically bounded intra-firm spillovers (internal agglomeration economies) and geographically bounded inter-firm spillovers (external agglomeration economies) on firms' location strategies. Using data from the Census Bureau's Longitudinal Business Database and the U.S. Cluster Mapping Project, we analyze organic expansions of biopharmaceutical firms (by both new establishments and employment increase in existing establishments) in the U.S. in 1993-2005. We consider all activities in the value chain and allow location choices to vary by R&D, manufacturing, and sales. Our findings suggest that (1) internal and external agglomeration economies have separate, positive impacts on location, with relevant differences by activity; (2) internal economies of agglomeration arise within an activity (e.g., among plants) and across activities (e.g., between manufacturing and sales); (3) the effects of internal economies across and within activities vary by activity and type of organic expansion; and (4) across-activity internal economies are asymmetric.
View Full
Paper PDF
-
Micro Data and the Macro Elasticity of Substitution
March 2012
Working Paper Number:
CES-12-05
We estimate the aggregate elasticity of substitution between capital and labor in the US manufacturing sector. We show that the aggregate elasticity of substitution can be expressed as a simple function of plant level structural parameters and sufficient statistics of the distribution of plant input cost shares. We then use plant level data from the Census of Manufactures to construct a local elasticity of substitution at various levels of aggregation. Our approach does not assume the existence of a stable aggregate production function, as we build up our estimate from the cross section of plants at a point in time. Accounting for substitution within and across plants, we find that the aggregate elasticity is substantially below unity at approximately 0.7. Lastly we assess the sources of the bias of aggregate technical change from 1987 to 1997. We find that the labor augmenting character of aggregate technical change is due almost exclusively to labor augmenting productivity growth at the plant level rather than relative growth in capital intensive plants.
View Full
Paper PDF
-
Modeling Single Establishment Firm Returns to the 2007 Economic Census
September 2011
Working Paper Number:
CES-11-28
The Economic Census is one of the most important activities that the U.S. Census Bureau performs. It is critical for updating firm ownership/structure and industry information for a large number of businesses in the Census Bureau's Business Register, impacting most other economic programs. Also, it feeds into Bureau of Economic Analysis products, such as benchmark inputoutput accounts and Gross Domestic Product. The overall check-in rate for the 2007 Economic Census was just over 86%. Establishments owned by multi-location companies returned over 90% of their forms, as compared to the roughly two million single-establishment firms sampled in the Census that returned just over 80%. We model the check-in rate for single-establishment firms by using a large number of variables that might be correlated with whether or not a firm returns a form in the Economic Census. These variables are broadly categorized as the characteristics of firms, measures of external factors, and features of the survey design. We use the model for two purposes. First, by including many of the factors that may be correlated with returns we aim to focus limited advertising and outreach resources to low-return segments of the population. Second, we use the model to investigate the efficacy of an unplanned intervention expected to increase return rates: using certified mailing for one of the form follow-ups.
View Full
Paper PDF
-
Using the Survey of Plant Capacity to Measure Capital Utilization
July 2011
Working Paper Number:
CES-11-19
Most capital in the United States is idle much of the time. By some measures, the average workweek of capital in U.S. manufacturing is as low as 55 hours per 168 hour week. The level and variability of capital utilization has important implications for understanding both the level of production and its cyclical fluctuations. This paper investigates a number of issues relating to aggregation of capital utilization measures from the Survey of Plant Capacity and makes recommendations on expanding and improving the published statistics deriving from the Survey of Plant Capacity. The paper documents a number of facts about properties of capital utilization. First, after growing for decades, capital utilization started to fall in mid 1990s. Second, capital utilization is a useful predictor of changes in capacity utilization and other factors of production. Third, adjustment of productivity measures for variable capital utilization improves statistical and economic properties of these measures. Fourth, the paper constructs weights to aggregate firm level capital utilization rates to industry and economy level, which is the major enhancement to available data.
View Full
Paper PDF
-
The Impact of Plant-Level Resource Reallocations and Technical Progress on U.S. Macroeconomic Growth
December 2009
Working Paper Number:
CES-09-43
We build up from the plant level an "aggregate(d) Solow residual" by estimating every U.S. manufacturing plant's contribution to the change in aggregate final demand between 1976 and 1996. We decompose these contributions into plant-level resource reallocations and plant-level technical efficiency changes. We allow for 459 different production technologies, one for each 4- digit SIC code. Our framework uses the Petrin and Levinsohn (2008) definition of aggregate productivity growth, which aggregates plant-level changes to changes in aggregate final demand in the presence of imperfect competition and other distortions and frictions. On average, we find that aggregate reallocation made a larger contribution than aggregate technical efficiency growth. Our estimates of the contribution of reallocation range from 1:7% to2:1% per year, while our estimates of the average contribution of aggregate technical efficiency growth range from 0:2% to 0:6% per year. In terms of cyclicality, the aggregate technical efficiency component has a standard deviation that is roughly 50% to 100% larger than that of aggregate total reallocation, pointing to an important role for technical efficiency in macroeconomic fluctuations. Aggregate reallocation is negative in only 3 of the 20 years of our sample, suggesting that the movement of inputs to more highly valued activities on average plays a stabilizing role in manufacturing growth.
View Full
Paper PDF
-
Discretionary Disclosure in Financial Reporting: An Examination Comparing Internal Firm Data to Externally Reported Segment Data
September 2009
Working Paper Number:
CES-09-28
We use confidential, U.S. Census Bureau, plant-level data to investigate aggregation in external reporting. We compare firms' plant-level data to their published segment reports, conducting our tests by grouping a firm's plants that share the same four-digit SIC code into a 'pseudo-segment.' We then determine whether that pseudo-segment is disclosed as an external segment, or whether it is subsumed into a different business unit for external reporting purposes. We find pseudo-segments are more likely to be aggregated within a line-of-business segment when the agency and proprietary costs of separately reporting the pseudo-segment are higher and when firm and pseudo-segment characteristics allow for more discretion in the application of segment reporting rules. For firms reporting multiple external segments, aggregation of pseudo-segments is driven by both agency and proprietary costs. However, for firms reporting a single external segment, we find no evidence of an agency cost motive for aggregation.
View Full
Paper PDF
-
Using the P90/P10 Index to Measure U.S. Inequality Trends with Current Population Survey Data: A View From Inside the Census Bureau Vaults
June 2007
Working Paper Number:
CES-07-17
The March Current Population Survey (CPS) is the primary data source for estimation of levels and trends in labor earnings and income inequality in the USA. Time-inconsistency problems related to top coding in theses data have led many researchers to use the ratio of the 90th and 10th percentiles of these distributions (P90/P10) rather than a more traditional summary measure of inequality. With access to public use and restricted-access internal CPS data, and bounding methods, we show that using P90/P10 does not completely obviate time inconsistency problems, especially for household income inequality trends. Using internal data, we create consistent cell mean values for all top-coded public use values that, when used with public use data, closely track inequality trends in labor earnings and household income using internal data. But estimates of longer-term inequality trends with these corrected data based on P90/P10 differ from those based on the Gini coefficient. The choice of inequality measure matters.
View Full
Paper PDF
-
What Causes Industry Agglomeration? Evidence from Coagglomeration Patterns
April 2007
Working Paper Number:
CES-07-13
Many industries are geographically concentrated. Many mechanisms that could account for such agglomeration have been proposed. We note that these theories make different predictions about which pairs of industries should be coagglomerated. We discuss the measurement of coagglomeration and use data from the Census Bureau's Longitudinal Research Database from 1972 to 1997 to compute pairwise coagglomeration measurements for U.S. manufacturing industries. Industry attributes are used to construct measures of the relevance of each of Marshall's three theories of industry agglomeration to each industry pair: (1) agglomeration saves transport costs by proximity to input suppliers or final consumers, (2) agglomeration allows for labor market pooling, and (3) agglomeration facilitates intellectual spillovers. We assess the importance of the theories via regressions of coagglomeration indices on these measures. Data on characteristics of corresponding industries in the United Kingdom are used as instruments. We find evidence to support each mechanism. Our results suggest that input-output dependencies are the most important factor, followed by labor pooling.
View Full
Paper PDF
