Visual Analytics for Model Selection in Time Series Analysis

Teaser Image
Author
Keywords
Abstract
Model selection in time series analysis is a challenging task for domain experts in many application areas such as epidemiology, economy, or environmental sciences. The methodology used for this task demands a close combination of human judgement and automated computation. However, statistical software tools do not adequately support this combination through interactive visual interfaces. We propose a Visual Analytics process to guide domain experts in this task. For this purpose, we developed the TiMoVA prototype that implements this process based on user stories and iterative expert feedback on user experience. The prototype was evaluated by usage scenarios with an example dataset from epidemiology and interviews with two external domain experts in statistics. The insights from the experts' feedback and the usage scenarios show that TiMoVA is able to support domain experts in model selection tasks through interactive visual interfaces with short feedback cycles. 
French Abstract
Notes
Custom 1
Custom 2
Custom 3
Custom 4
Custom 5
Custom 6
Custom 7
Author Address
Year of Publication
2013
Journal
IEEE Transactions on Visualization and Computer Graphics, Special Issue "VIS 2013"
Volume
19
Issue
12
Number of Pages
2237 - 2246
Date Published
12/2013
ISSN Number
1077-2626
Citation Key
URL
http://publik.tuwien.ac.at/files/PubDat_220251.pdf
DOI
10.1109/TVCG.2013.222
Research Notes
Funding projects
Video Link
Supplementary Material