Multiple Outlier Detection Tests for Parametric Models
We propose a simple multiple outlier identification method for parametric location-scale and shape-scale models when the number of possible outliers is not specified. The method is based on a result giving asymptotic properties of extreme <i>z</i>-scores. Robust estimators of model param...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/8/12/2156 |
| _version_ | 1797545809179312128 |
|---|---|
| author | Vilijandas Bagdonavičius Linas Petkevičius |
| author_facet | Vilijandas Bagdonavičius Linas Petkevičius |
| author_sort | Vilijandas Bagdonavičius |
| collection | DOAJ |
| description | We propose a simple multiple outlier identification method for parametric location-scale and shape-scale models when the number of possible outliers is not specified. The method is based on a result giving asymptotic properties of extreme <i>z</i>-scores. Robust estimators of model parameters are used defining z-scores. An extensive simulation study was done for comparing of the proposed method with existing methods. For the normal family, the method is compared with the well known Davies-Gather, Rosner’s, Hawking’s and Bolshev’s multiple outlier identification methods. The choice of an upper limit for the number of possible outliers in case of Rosner’s test application is discussed. For other families, the proposed method is compared with a method generalizing Gather-Davies method. In most situations, the new method has the highest outlier identification power in terms of masking and swamping values. We also created R package outliersTests for proposed test. |
| first_indexed | 2024-03-10T14:20:21Z |
| format | Article |
| id | doaj.art-4a5a3bf128c14e6fb8ae777ac6fa9820 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T14:20:21Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-4a5a3bf128c14e6fb8ae777ac6fa98202023-11-20T23:24:11ZengMDPI AGMathematics2227-73902020-12-01812215610.3390/math8122156Multiple Outlier Detection Tests for Parametric ModelsVilijandas Bagdonavičius0Linas Petkevičius1Institute of Applied Mathematics, Vilnius University, Naugarduko 24, LT-03225 Vilnius, LithuaniaInstitute of Computer Science, Vilnius University, Didlaukio 47, LT-08303 Vilnius, LithuaniaWe propose a simple multiple outlier identification method for parametric location-scale and shape-scale models when the number of possible outliers is not specified. The method is based on a result giving asymptotic properties of extreme <i>z</i>-scores. Robust estimators of model parameters are used defining z-scores. An extensive simulation study was done for comparing of the proposed method with existing methods. For the normal family, the method is compared with the well known Davies-Gather, Rosner’s, Hawking’s and Bolshev’s multiple outlier identification methods. The choice of an upper limit for the number of possible outliers in case of Rosner’s test application is discussed. For other families, the proposed method is compared with a method generalizing Gather-Davies method. In most situations, the new method has the highest outlier identification power in terms of masking and swamping values. We also created R package outliersTests for proposed test.https://www.mdpi.com/2227-7390/8/12/2156location-scale modelsoutliers identificationunknown number of outliersoutlier regionrobust estimators |
| spellingShingle | Vilijandas Bagdonavičius Linas Petkevičius Multiple Outlier Detection Tests for Parametric Models Mathematics location-scale models outliers identification unknown number of outliers outlier region robust estimators |
| title | Multiple Outlier Detection Tests for Parametric Models |
| title_full | Multiple Outlier Detection Tests for Parametric Models |
| title_fullStr | Multiple Outlier Detection Tests for Parametric Models |
| title_full_unstemmed | Multiple Outlier Detection Tests for Parametric Models |
| title_short | Multiple Outlier Detection Tests for Parametric Models |
| title_sort | multiple outlier detection tests for parametric models |
| topic | location-scale models outliers identification unknown number of outliers outlier region robust estimators |
| url | https://www.mdpi.com/2227-7390/8/12/2156 |
| work_keys_str_mv | AT vilijandasbagdonavicius multipleoutlierdetectiontestsforparametricmodels AT linaspetkevicius multipleoutlierdetectiontestsforparametricmodels |