Predicting the Achievement of SDG 8: Decent Work and Economic Growth. Empirical Bayes Approach

This paper focuses on the prediction of achievement of one of the Sustainable Development Goals, Goal 8: Decent Work and Economic Growth, across the world. The panel data structure enables to use recently proposed empirical Bayes approach. It focuses on obtaining the individual-specific intercept parameters, instead of removing them from the model and treating them as a nuisance, as it is usually happening in most of the popular and widely used methods for linear dynamic panel data models. Application of the methodology on various data sets with different characteristics points out both the advantages and disadvantages of the method. It has been shown that in certain settings the proposed models may perform better than the chosen benchmark models. Consequently, modelling the individual intercept may lead to increase in the prediction accuracy. The method also works quite well with very short time series.