This website uses third party cookies to improve your experience. If you continue browsing or close this notice, you will accept their use.

Giuseppe Brandi (LUISS)

23 November 2016 at 1:00 PM - 2:30 PM

Room 404a, Campus on Viale Romania, 32

Speaker: Giuseppe Brandi
  • Speaker:  Giuseppe Brandi (LUISS)
  • Title:  Tensor Autoregression in Economics and Finance
  • Abstract:  The Increase of multidimensional data poses a problem in its analysis. Standard methods reduce the multidimensional date on vectors or matrices and do analysis on this simpler objects. However, this approach has two main drawbacks. The first one related to the repute in vectorize a multidimensional dataset destroys the interconnections between dimensions and Secondly, there it Generates an exponentially Increase of the parameters to be estimated. A common way to reduce the number of variables to be estimated is to use PCA methods, but as it is known, PCA factors are then difficult to interpret. A way to overcome this problem is to rely on tensor analysis. Treating the dataset as a tensor (a multidimensional matrix) and fitting a model on it, gives us The Possibility to be parsimonious on the number of parameters to estimate without destroying interconnections. In this work we employ multilinear algerba and tensor calculus to build a Tensor (Auto) regression model for multidimensional Economic date.