Search Results

You are looking at 1 - 10 of 295 items for :

  • Refine by Access: All Content x
Clear All

The paper describes a few cases of different type outliers and possibilities to eliminate their disturbing (or meaningful) effect.

Restricted access

. Therefore, this paper proposes a new method to detect distinctive patents that can act as technological opportunities at the individual patent level by exploiting subject–action–object (SAO)-based semantic patent analysis and outlier detection. SAO

Restricted access

We address the further improvements and clarifications to the formal and categorizing definition of outlier given by Monhor and Takemoto (2005), by means of integrating to the above definition the subclass of valuable outliers introduced by Verő (2009). The concrete illustrative examples taken from geophysics and other areas, and the further remarks on and insights into the nature of outliers presented in this paper are, to a certain extent, the contributions to the establishment of such a categorization that integrates the diverse and heterogenous appearance of outliers and helps the comprehensive grasp of the concept of outlier.

Restricted access

In the last decades many statistical tests based on the least squares solution have been proposed for multiple outlier detection. All of them suffer, however, from deficiencies that make them inefficient in their practical application. As recently demonstrated by the author, this situation is unavoidable in the framework of least squares theory. The present contribution elaborates on this impossibility of obtaining an unambiguous response for any statistical test based on the least squares solution and makes use of multiple least squares adjustments for statistically characterizing the equivalent sets of multiple gross error vectors. Several examples and a flexible Matlab implementation are provided.

Restricted access

In this article, we propose a technique for the precise cleaning of the gravity anomaly database based on the cross validation approach. The terrestrial gravity anomalies were compared versus a global geopotential model and take into account the effect of topography in this comparison. The efficiency of the cross-validation technique is illustrated in outlier detection as well as in choosing the proper gridding technique as a case study in construction of the Iranian new gravity database. In order to reduce the effect of topography and the discretisation error, a special interpolation scheme is used for gridding of the free-air gravity anomalies. The final grid file was created based on the Kriging method with 80″ × 90″ block resolution. The overall accuracy for the new Iranian gravity database is estimated in the order of 10 mGal.

Restricted access

Outliers in geodetic networks badly affect all parameters and their variances estimated by least-squares. Tests for outliers (e.g. Baarda’s and Pope’s tests) are frequently used to detect outliers in geodetic networks. To measure the ability of these tests, the mean success rate (MSR) is proposed. Studies have shown that the MSRs of these tests in geodetic networks are low due to the smearing effect of the least-squares estimation even if there is only one outlier in the data set. In this paper, a new approach, for small outliers, is presented to increase the MSRs of the tests for outliers in geodetic networks. The main idea is that if the weight of one observation is increased, the corresponding studentized or normalized residuals are increased, too. This thesis is proved. Hence, the ability of the tests to detect outliers can be increased by appropriately increasing the weight of one observation at a time and repeating this for all observations. This approach is applied to three simulated geodetic networks. We show that the MSRs of the outlier tests are improved by approximately 5% if there is one small outlier in the data set. However, the improvements in the MSRs for more than one outlier are low.

Restricted access

Geodetic measurements are commonly used for monitoring volcanic activities and crustal motions. Together with paleoseismic and other geologic observations, geodetic data are central in long-term forecast of earthquake hazards. Presence of outliers in geodetic data strongly affects least squares principle, which are extensively used for data analysis and modeling in geodesy. Thus, the positions of the geodetic points are computed as biased. Robust methods are techniques used to construct estimates describing well data majority. In this study, some robust methods and conventional tests for outliers have been tested on a number of linear and nonlinear geodetic adjustment models. The results are presented to illustrate the effectiveness of the methods. Furthermore, we discuss how the effectiveness of the methods changes depending on various key parameters for geodetic networks, i.e. the number of outliers, the magnitude of outliers, the degree of freedom, the number of observation and number of unknowns.

Restricted access

The problem of handling outliers in a deformation monitoring network is of special importance, because the existence of outliers may lead to false deformation parameters. One of the approaches to detect the outliers is to use robust estimators. In this case the network points are computed by such a robust method, implying that the adjustment result is resisting systematic observation errors, and, in particular, it is insensitive to gross errors and even blunders. Since there are different approaches to robust estimation, the resulting estimated networks may differ. In this article, different robust estimation methods, such as the M-estimation of Huber, the “Danish”, and the L 1 -norm estimation methods, are reviewed and compared with the standard least squares method to view their potentials to detect outliers in the Tehran Milad tower deformation network. The numerical studies show that the L 1 -norm is able to detect and down-weight the outliers best, so it is selected as the favourable approach, but there is a lack of uniqueness. For comparison, Baarda’s method “data snooping” can achieve similar results when the outlier magnitude of an outlier is large enough to be detected; but robust methods are faster than the sequential data snooping process.

Restricted access

Abstract  

This paper describes experimental results through multivariate statistical methods that might reveal outliers that are rarely taken into account by analysts. The results were submitted to three procedures to detect outliers: Mahalanobis distance, MD, cluster analysis, CA, and principal component analysis, PCA. The results showed that although CA is one of the procedures most often used to identify outliers, it can fail by not showing the samples that are easily identified as outliers by other methods, like MD. Mahalanobis distance proved to be the simpler application, with sensitive procedures to identify outliers in multivariate datasets.

Restricted access
Scientometrics
Authors:
Stephen Carley
and
Alan L. Porter

processes and interactions. Appendix B: Cited papers within each benchmark that have at least 3 CSCs We note from this figure that Math, once again, is the outlier. The remaining five benchmarks display

Restricted access