engleski

An econometric model for development level assessment with an application to municipality development classification

In this paper a multivariate statistical method for assessing the level of development is presented and applied to the Croatian territorial units. The main aim is to achieve a classification of the territorial units, in this case municipalities, according to their development level, in order to provide a development level information inputs for the policy makers. Development assessment is based on three dimensions: economic, based on the economic wealth of the population, structural, based on the unemployment issue and demographic, based on the demographic structure of the population and the level of education. Each dimension was formulated as factor analytic model and subsequently tested using maximum likelihood factor analysis. Based on these results a structural equation model with latent variable was estimated and subsequently computed latent scores from the structural model were used in hierarchical and K-means cluster analysis methods. The results enabled estimation of the latent development level of the territorial units and development-ranking of all territorial units on an interval scale in respect to their latent development level as well as non-interval clustering. In addition, a territorial development classification was proposed based on economic, structural and demographic criteria (factors). The results of the research showed that in situation where GDP per capita data are missing, efficient estimation of the development level using multivariate approach is possible.

municipality development classification; econometric models

nije evidentirano