Abstract
This paper responds to the following question, namely, when we have interval values for the observations, what is the interval of possible values of their variance. In parallel, we provide a response to the same question when the variance is replaced by the mean of the absolute values of the residuals from the median. Several solutions ranging from the linear and quadratic programming to different search algorithms are discussed.
Similar content being viewed by others
References
Coleman T, Branch MA, Grace A (1999) Optimization toolbox for use with Matlab. The MathWorks, Natick
Computational Statistics (2006) Special Issue on Interval Data, 21(2)
Ferson et al. Computing variance for interval data is NP-hard. http://www.cs.utep.edu/vladik/2002/tr02-13b.pdf
Gioia F, Lauro NC (2006) Principal component analysis on interval data. Comput Stat 21(2): 243–263
Kreinovich V et al (2006) Towards combining probabilistic and interval uncertainty in engineering calculations: algorithms for computing statistics under interval uncertainty, and their computational complexity. Reliab Comput 12: 471–501
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Antoch, J., Brzezina, M. & Miele, R. A note on variability of interval data. Comput Stat 25, 143–153 (2010). https://doi.org/10.1007/s00180-009-0166-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-009-0166-8