Visual Analytics for Model Selection in Time Series Analysis

TitleVisual Analytics for Model Selection in Time Series Analysis
Publication TypeJournal Article
Year of Publication2013
AuthorsBögl, M., W. Aigner, P. Filzmoser, T. Lammarsch, S. Miksch, and A. Rind
Journal IEEE Transactions on Visualization and Computer Graphics, Special Issue "VIS 2013"
Volume19
Issue12
Pages2237 - 2246
Date Published12/2013
ISSN1077-2626
Keywordscoordinated & multiple views, model selection, time series analysis, Visual analytics, visual interaction
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. 

Notes

URLhttp://publik.tuwien.ac.at/files/PubDat_220251.pdf
DOI10.1109/TVCG.2013.222
Full Text
Funding projects: 
CVAST
Funding projects: 
HypoVis