The University of Southampton
University of Southampton Institutional Repository

Labour force estimation for small areas in Venezuela

Labour force estimation for small areas in Venezuela
Labour force estimation for small areas in Venezuela

This thesis focuses on the problem of producing reliable estimates of Employment, Unemployment and Activity rates by Sex-age groups for Venezuelan States using the Population Census as auxiliary information. This is a common situation in the Latin-American region. The SPREE approach to Small Area Estimation is suited to dealing with this sort of problem. Although the use of SPREE methods in the SAE context has been treated in the literature, its use for estimation of product multinomial variables as well as a general methodology for variance estimation was largely unexplored.

There are some potential barriers to the convenient application of SPREE methods. To start, we note that SPREE involves application of the Iterative Proportional Fitting (IPF) algorithm which often requires the development of "domestic" computational algorithms. Besides this, the general computation of variance estimates for SPREE is not obvious. To address these issues, we established a link between SPREE methods, Log-linear models and Logistic models allowing the integration of complex sampling designs via the Pseudo-Likelihood approach to estimation. The main attraction of such a link is that it offers the possibility of implementing SPREE from a GLM perspective. We then show the equivalence of the Log-linear and Logistic versions of SPREE to the application of the well known "Exposure" technique from regression theory. This equivalence allows us to easily implement SPREE, computing parameter and variance estimates as well as goodness of fit measures and related diagnostic, using standard commercial statistical software. Overall, the approach to SPREE presented in this thesis makes this technique more flexible and accessible for practical application.

The "exposure" approach to SPREE was used in an empirical analysis of the Venezuelan labour force, including a simulation study to examine the properties of the estimators considered in this thesis. Superiority of the SPREE method over design-based estimators when the former is based on a good reference table was evident. However, conventional logistic model-based estimators can be regarded as favourable alternatives to SPREE-based estimators in situations when there is a reasonable doubt about the quality of the available reference information.

University of Southampton
Seijas-Rodriguez, Felix L
ff267660-7053-4411-9ce1-c14dc3c32844
Seijas-Rodriguez, Felix L
ff267660-7053-4411-9ce1-c14dc3c32844

Seijas-Rodriguez, Felix L (2002) Labour force estimation for small areas in Venezuela. University of Southampton, Doctoral Thesis.

Record type: Thesis (Doctoral)

Abstract

This thesis focuses on the problem of producing reliable estimates of Employment, Unemployment and Activity rates by Sex-age groups for Venezuelan States using the Population Census as auxiliary information. This is a common situation in the Latin-American region. The SPREE approach to Small Area Estimation is suited to dealing with this sort of problem. Although the use of SPREE methods in the SAE context has been treated in the literature, its use for estimation of product multinomial variables as well as a general methodology for variance estimation was largely unexplored.

There are some potential barriers to the convenient application of SPREE methods. To start, we note that SPREE involves application of the Iterative Proportional Fitting (IPF) algorithm which often requires the development of "domestic" computational algorithms. Besides this, the general computation of variance estimates for SPREE is not obvious. To address these issues, we established a link between SPREE methods, Log-linear models and Logistic models allowing the integration of complex sampling designs via the Pseudo-Likelihood approach to estimation. The main attraction of such a link is that it offers the possibility of implementing SPREE from a GLM perspective. We then show the equivalence of the Log-linear and Logistic versions of SPREE to the application of the well known "Exposure" technique from regression theory. This equivalence allows us to easily implement SPREE, computing parameter and variance estimates as well as goodness of fit measures and related diagnostic, using standard commercial statistical software. Overall, the approach to SPREE presented in this thesis makes this technique more flexible and accessible for practical application.

The "exposure" approach to SPREE was used in an empirical analysis of the Venezuelan labour force, including a simulation study to examine the properties of the estimators considered in this thesis. Superiority of the SPREE method over design-based estimators when the former is based on a good reference table was evident. However, conventional logistic model-based estimators can be regarded as favourable alternatives to SPREE-based estimators in situations when there is a reasonable doubt about the quality of the available reference information.

Text
842700.pdf - Version of Record
Available under License University of Southampton Thesis Licence.
Download (6MB)

More information

Published date: 2002

Identifiers

Local EPrints ID: 464682
URI: http://eprints.soton.ac.uk/id/eprint/464682
PURE UUID: ffb68024-2e22-4d6e-aa94-8487ba7ec666

Catalogue record

Date deposited: 04 Jul 2022 23:56
Last modified: 16 Mar 2024 19:41

Export record

Contributors

Author: Felix L Seijas-Rodriguez

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×