Multilevel models and small area estimation in the context of Vietnam living standards surveys

Type Journal Article
Title Multilevel models and small area estimation in the context of Vietnam living standards surveys
Author(s)
Publication (Day/Month/Year) 2010
URL https://hal.inria.fr/inria-00494741/document
Abstract
This talk will discuss a methodology to obtain small area estimates in the context of the Vietnam Living Standards Surveys. The presentation will proceed in three parts. First we will introduce the Viet Nam Living Standards Surveys, their historical development, topics covered, sample size issues and challenges. Second, we will briefly review main concepts in small area estimation, including the use of auxiliary data, and will contrast simplesmall area models with regression small area models. This will then lead to the notion of random effects in small area regression models, and to our proposed multilevel model for small area estimation at the commune level in Vietnam, to our knowledge the first such model built with Vietnam living standards data. The third part of the talk will discuss this model. Our proposed multilevel model for estimating the commune-level mean (log of) household expenditureper capita relies on independent variables available both in the 1999 Census and in the Vietnam Household Living Standards Survey of 2002. Following ideas given in work by Moura (1994, 1999), the small area estimation is performed by plugging the population means of the independent variables into the regression equation, inclusive of suitable random effects both in the intercept and in the coefficient of the dummy variable for the urban location of ahousehold. We will discuss how the random effects in the model can also be used to examine the urban-rural gapacross the country. We will also mention how to measure the accuracy of our small area estimators. Finally, we will touch upon the use of sampling weights in models such as presented in the talk.

Related studies

»
»
»