Search

The purpose of this paper is to investigate the application of a generalized dynamic factor model (GDFM) based on dynamic principal components analysis to forecasting short-term economic growth in Romania. We have used a generalized principal components approach to estimate a dynamic model based on a dataset comprising 86 economic and non-economic variables that are linked to economic output. The model exploits the dynamic correlations between these variables and uses three common components that account for roughly 72% of the information contained in the original space. We show that it is possible to generate reliable forecasts of quarterly real gross domestic product (GDP) using just the common components while also assessing the contribution of the individual variables to the dynamics of real GDP. In order to assess the relative performance of the GDFM to standard models based on principal components analysis, we have also estimated two Stock-Watson (SW) models that were used to perform the same out-of-sample forecasts as the GDFM. The results indicate significantly better performance of the GDFM compared with the competing SW models, which empirically confirms our expectations that the GDFM produces more accurate forecasts when dealing with large datasets. [ABSTRACT FROM AUTHOR]

The purpose of my research is to find a method by which the acquisition of the abstract algebraical thinking can be made efficient in the case of Romany students coming from a socially underprivileged background, through text-based problems. I teach in School no. 1 of Diosig, in Romania, where the rate of Romany minority is of 23%, while more than a half of the children studying in Hungarian at school come from Romany families. The research was conducted in this school. The essence of this method is that I do not teach the algebraic operations, the algebraic method of solving text-based problems, which is to be acquired in the seventh grade, the way the Romanian educational system requires, that is to start from theoretical bases, but I build every item to be learnt around text-based problems. We revised the basic operations by text-based problems, then we introduced the notion of variable through games similarly formulated by texts and calculated the substitute values. They deduced and learnt the reduction of the variables through text-based problems, as well, by an inductive sequence. [ABSTRACT FROM AUTHOR]