Sampling plan for socioeconomic development indicators in Brazil: practical implications when considering precision and cost

Abstract

Socioeconomic development indicators such as Income, Human Development Index, and Gini Index have explained recent deforestation events in Brazil. These indicators, obtained from the demographic census, are expensive and are released every ten years. Despite being costly, they are important descriptors of the phenomenon of deforestation that occurs in one of the most relevant ecosystems in the world, the Brazilian forests. Therefore, the objective in this study was to detect the most representative and the lowest costly sample in order to obtain the referred indicators, from Brazilian municipalities from 2000 to 2010. The sample mean and confidence interval were obtained to be compared with the population average. The mean and confidence interval estimators come from 1,000 resamples according to simple random sampling and stratified random by geographic region. We evaluated the following sample intensities: 10%, 20%, 30%, 40% and 50% of the Brazilian municipalities. The results indicated that: a) 10% of Brazilian municipalities are sufficient to represent Income, HDI and Gini; b) We recommend both random and stratified sampling when selecting the municipalities that will provide the HDI and Gini values, on the contrary, for Income, the indicated sampling is the stratified one. These results show the importance of applied research in sampling and simulation to optimize the survey of demographic data collection, in a situation of budgetary constraint, in countries of vast dimensions such as Brazil. This study can increase understanding of the importance of socioeconomic development indicators to estimating progressive forest loss in Brazil, the country with the largest rainforest in the world.