A Full Distribution Approach to Simulating the Industry Aggregate in the Input-Output Modeling Framework
Jackson, Randall Wade
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/70641
Description
Title
A Full Distribution Approach to Simulating the Industry Aggregate in the Input-Output Modeling Framework
Author(s)
Jackson, Randall Wade
Issue Date
1983
Department of Study
Geography
Discipline
Geography
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Geography
Abstract
A full distribution approach is presented as an alternative to conventional aggregate variable representation in input-output (IO) analysis, and its implications and viability are explored. The basic supposition is that those macrolevel variables that are simple or weighted averages of samples from microlevel component distributions are most often poor representations of their underlying populations. This is supported by a number of theoretical arguments, and an aggregation experiment employing the 1972 United States national commodity-industry accounts. A representation of the full distribution of microlevel components by a theoretical probability density function (pdf) is introduced as an alternative to the traditional point estimate, given the varied and strongly skewed observed production coefficient distributions.
The theoretical gamma density is chosen for application in the IO simulation. Distributions of row and column multipliers and gross output vectors are generated and analyzed. Relative variance observed is half again as large for output vector as for multiplier distributions.
A number of significant implications are derived. At the general level, it is shown that the full distribution approach enables interval estimates for traditionally deterministic models that generate only point estimates. Where aggregate variable interrelationships are nonlinear, the expected values of the resulting distributions are different from and superior to the conventional point estimates. The implementation of the full distribution approach requires no restrictive assumptions regarding the relationships among the microlevel attributes represented by the theoretical pdf. However, prior information concerning these relationships can be easily incorporated. The approach generally requires no additional microlevel data since it employs the same data necessary for traditional aggregate variable formulation.
In a spatial context, it is shown that the full distribution approach provides a foundation for procedures that can be implemented to: (1) estimate interregional trade coefficients; (2) adapt existing IO tables to regions for which no table currently exists; and (3) adjust IO coefficients over space and time. Finally, the variation among region specific industry pdf's offers insights into the structure of the space economy.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
