Analytic Derivatives for Estimation of Linear Dynamic Models
November 1988
Working Paper Number:
CES-88-05
Abstract
This paper develops two algorithms. Algorithm I computes the exact, Gaussian, log-likelihood function, its exact, gradient vector, and an asymptotic approximation of its Hessian matrix, for discrete-time, linear, dynamic models in state-space form. Algorithm 2, derived from algorithm I, computes the exact, sample, information matrix of this likelihood function. The computed quantities are analytic (not numerical approximations) and should, therefore, be useful for reliably, quickly, and accurately: (i) checking local identifiability of parameters by checking the rank of the information matrix; (ii) using the gradient vector and Hessian matrix to compute maximum likelihood estimates of parameters with Newton methods; and, (iii) computing asymptotic covariances (Cramer-Rao bounds) of the parameter estimates with the Hessian or the information matrix. The principal contribution of the paper is algorithm 2, which extends to multivariate models the univariate results of Porat and Friedlander (1986). By relying on the Kalman filter instead of the Levinson-Durbin filter used by Porat and Friedlander, algorithms 1 and 2 can automatically handle any pattern of missing or linearly aggregated data. Although algorithm 1 is well known, it is treated in detail in order to make the paper self contained.
Document Tags and Keywords
Keywords
Keywords are automatically generated using KeyBERT, a powerful and innovative
keyword extraction tool that utilizes BERT embeddings to ensure high-quality and contextually relevant
keywords.
By analyzing the content of working papers, KeyBERT identifies terms and phrases that capture the essence of the
text, highlighting the most significant topics and trends. This approach not only enhances searchability but
provides connections that go beyond potentially domain-specific author-defined keywords.
:
Tags
Tags are automatically generated using a pretrained language model from spaCy, which excels at
several tasks, including entity tagging.
The model is able to label words and phrases by part-of-speech,
including "organizations." By filtering for frequent words and phrases labeled as "organizations", papers are
identified to contain references to specific institutions, datasets, and other organizations.
:
Similar Working Papers
Similarity between working papers are determined by an unsupervised neural
network model
know as Doc2Vec.
Doc2Vec is a model that represents entire documents as fixed-length vectors, allowing for the
capture of semantic meaning in a way that relates to the context of words within the document. The model learns to
associate a unique vector with each document while simultaneously learning word vectors, enabling tasks such as
document classification, clustering, and similarity detection by preserving the order and structure of words. The
document vectors are compared using cosine similarity/distance to determine the most similar working papers.
Papers identified with 🔥 are in the top 20% of similarity.
The 10 most similar working papers to the working paper 'Analytic Derivatives for Estimation of Linear Dynamic Models' are listed below in order of similarity.
-
Working PaperWorkers' Job Prospects and Young Firm Dynamics
January 2025
Working Paper Number:
CES-25-09
This paper investigates how worker beliefs and job prospects impact the wages and growth of young firms, as well as the aggregate economy. Building a heterogeneous-firm directed search model where workers gradually learn about firm types, I find that learning generates endogenous wage differentials for young firms. High-performing young firms must pay higher wages than equally high-performing old firms, while low-performing young firms offer lower wages than equally low-performing old firms. Reduced uncertainty or labor market frictions lower the wage differentials, thereby enhancing young firm dynamics and aggregate productivity. The results are consistent with U.S. administrative employee-employer matched data.View Full Paper PDF
-
Working PaperWhy the Economics Profession Must Actively Participate in the Privacy Protection Debate
March 2019
Working Paper Number:
CES-19-09
When Google or the U.S. Census Bureau publish detailed statistics on browsing habits or neighborhood characteristics, some privacy is lost for everybody while supplying public information. To date, economists have not focused on the privacy loss inherent in data publication. In their stead, these issues have been advanced almost exclusively by computer scientists who are primarily interested in technical problems associated with protecting privacy. Economists should join the discussion, first, to determine where to balance privacy protection against data quality; a social choice problem. Furthermore, economists must ensure new privacy models preserve the validity of public data for economic research.View Full Paper PDF
-
Working PaperMarket Forces, Plant Technology, and the Food Safety Technology Use
June 2008
Working Paper Number:
CES-08-14
Economists (Ollinger and Mueller, 2003; Golan et al., 2004) have considered some of the economic forces, such as demands from major customers, that encourage plants to maintain food safety process control. Other economists, such as Roberts (2005), have identified food safety technologies that enable better control harmful pathogens. However, economists have not put the two together. The purpose of this paper is to examine the impact of economic forces, including firm effects and plant technology, customer demands, and regulation, on food safety technology use. Preliminary results suggest that customer demand has the greatest impact.View Full Paper PDF
-
Working PaperAccess Methods for United States Microdata
August 2007
Working Paper Number:
CES-07-25
Beyond the traditional methods of tabulations and public-use microdata samples, statistical agencies have developed four key alternatives for providing non-government researchers with access to confidential microdata to improve statistical modeling. The first, licensing, allows qualified researchers access to confidential microdata at their own facilities, provided certain security requirements are met. The second, statistical data enclaves, offer qualified researchers restricted access to confidential economic and demographic data at specific agency-controlled locations. Third, statistical agencies can offer remote access, through a computer interface, to the confidential data under automated or manual controls. Fourth, synthetic data developed from the original data but retaining the correlations in the original data have the potential for allowing a wide range of analyses.View Full Paper PDF
-
Working PaperSoft and Hard Within- and Between-Industry Changes of U.S. Skill Intensity: Shedding Light on Worker's Inequality
January 2006
Working Paper Number:
CES-06-01
In order to examine the worsening of inequality between workers of different skill levels over the past three decades and to further motivate the theoretical discussion on this issue, we use the decomposition methodology to focus on the interaction of within- and between-industry changes of the relative skill intensity in U.S. manufacturing. Unlike previous work, we use more detailed levels of industry classification (5-digit SIC product codes), and we analyze the impact of plants switching industries as well as of plant births and deaths on these changes. Internal, plant-level data from the U.S. Census Bureau's Longitudinal Research Database and the new Longitudinal Business Database provide us with the requisite information to conduct these studies. Finally, our empirical conclusions are discussed in relation to the inspired theoretical inference, as they enrich the debate concerning the sources of the inequality by justifying the skill-biased character of technical change.View Full Paper PDF
-
Working PaperEstimating market power Evidence from the US Brewing Industry
January 2017
Working Paper Number:
CES-17-06R
While inferring markups from demand data is common practice, estimation relies on difficult-to-test assumptions, including a specific model of how firms compete. Alternatively, markups can be inferred from production data, again relying on a set of difficult-to-test assumptions, but a wholly different set, including the assumption that firms minimize costs using a variable input. Relying on data from the US brewing industry, we directly compare markup estimates from the two approaches. After implementing each approach for a broad set of assumptions and specifications, we find that both approaches provide similar and plausible markup estimates in most cases. The results illustrate how using the two strategies together can allow researchers to evaluate structural models and identify problematic assumptions.View Full Paper PDF
-
Working PaperForeign Direct Investment, Geography, and Welfare
September 2024
Working Paper Number:
CES-24-45
We study the impact of FDI on domestic welfare using a model of internal trade with variable markups that incorporates intranational transport costs. The model allows us to disentangle the various channels through which FDI affects welfare. We apply the model to the case of Ethiopian manufacturing, which received considerable amounts of FDI during our study period. We find substantial gains from the presence of foreign firms, both in the local market and in other connected markets in the country. FDI, however, resulted in a modest worsening of allocative efficiency because foreign firms tend to have significantly higher markups than domestic firms. We report consistent findings from our empirical analysis, which utilises microdata on manufacturing firms, information on FDI projects, and geospatial data on improvements in the road network.View Full Paper PDF
-
Working PaperChanges in Metropolitan Area Definition, 1910-2010
February 2021
Working Paper Number:
CES-21-04
The Census Bureau was established as a permanent agency in 1902, as industrialization and urbanization were bringing about rapid changes in American society. The years following the establishment of a permanent Census Bureau saw the first attempts at devising statistical geography for tabulating statistics for large cities and their environs. These efforts faced several challenges owing to the variation in settlement patterns, political organization, and rates of growth across the United States. The 1910 census proved to be a watershed, as the Census Bureau offered a definition of urban places, established the first census tract boundaries for tabulating data within cities, and introduced the first standardized metropolitan area definition. It was not until the middle of the twentieth century, however, the Census Bureau in association with other statistical agencies had established a flexible standard metropolitan definition and a more consistent means of tabulating urban data. Since 1950, the rules for determining the cores and extent of metropolitan areas have been largely regarded as comparable. In the decades that followed, however, a number of rule changes were put into place that accounted for metropolitan complexity in differing ways, and these have been the cause of some confusion. Changes put into effect with the 2000 census represent a consensus of sorts for how to handle these issues.View Full Paper PDF
-
Working PaperPerson Matching in Historical Files using the Census Bureau's Person Validation System
September 2014
Working Paper Number:
carra-2014-11
The recent release of the 1940 Census manuscripts enables the creation of longitudinal data spanning the whole of the twentieth century. Linked historical and contemporary data would allow unprecedented analyses of the causes and consequences of health, demographic, and economic change. The Census Bureau is uniquely equipped to provide high quality linkages of person records across datasets. This paper summarizes the linkage techniques employed by the Census Bureau and discusses utilization of these techniques to append protected identification keys to the 1940 Census.View Full Paper PDF
-
Working PaperGrowing Oligopolies, Prices, Output, and Productivity
November 2018
Working Paper Number:
CES-18-48
American industries have grown more concentrated over the last forty years. In the absence of productivity innovation, this should lead to price hikes and output reductions, decreasing consumer welfare. Using public data from 1972-2012, I use price data to disentangle revenue from output. Difference-in-difference estimates show that industry concentration increases are positively correlated to productivity and real output growth, uncorrelated with price changes and overall payroll, and negatively correlated with labor's revenue share. I rationalize these results in a simple model of competition. Productive industries (with growing oligopolists) expand real output and hold down prices, raising consumer welfare, while maintaining or reducing their workforces, lowering labor's share of output.View Full Paper PDF
