Advances in mathematical statistics

Driven by the demand from modeling applications, the Advanced Systems Analysis (ASA) Program has been developing several different approaches to gaining information from data using mathematical statistics.

Data © antishock | iStock

Data

ASA scientists [1] developed and demonstrated the applicability of a new probabilistic non-Bayesian downscaling approach which has been applied to IIASA’s GLOBIOM modeling framework, used principally by the Ecosystems Services and Management Program (ESM). The approach is based on maximization of the Kulback-Leibler information distance (cross-entropy) between i) prior distributions of land cover changes for a given year and perceived scenarios of future changes, and ii) unknown distribution of land use patterns consistent with aggregate results from GLOBIOM.

Pairs of q-Gaussian distributions and suggested transformations of q-Gaussians on to one another [2]. This fact allows for convenient representation of these when they are used in non-ergodic and complex systems.

References

[1] Ermolieva T, Havlik P, Mosnier A, Obersteiner M, Ermoliev Y (2013). Dynamic recursive procedure for downscaling land cover changes from GLOBIOM model. IIASA Interim Report IR-13-005.
[2] Tateishi AA, Hanel R, Thurner S (2013). The transformation-groupoid structure of the q-Gaussian family. Physics Letters A, 377 (31-33), 1804—1809.

Collaborators

The work on downscaling of GLOBIOM for Ukraine is of relevance to the IIASA's Ukrainian National Member Organization.
ASA’s main collaborators in the field of Advances in statistics include D. Farmer, Professor, Oxford University, UK; M. Gell-Mann, Professor, Santa-Fe Institute, USA; Y. Holovatch, Professor, National Academy of Science, Ukraine; C. Mascolo, Professor, Cambridge University, UK.


Print this page

Last edited: 21 May 2014

CONTACT DETAILS

Elena Rovenskaya

Program Director

Advanced Systems Analysis

T +43(0) 2236 807 608

Further information

Events

Staff

International Institute for Applied Systems Analysis (IIASA)
Schlossplatz 1, A-2361 Laxenburg, Austria
Phone: (+43 2236) 807 0 Fax:(+43 2236) 71 313