• Title/Summary/Keyword: skipped median

Search Result 3, Processing Time 0.016 seconds

Least clipped absolute deviation for robust regression using skipped median

  • Hao Li;Seokho Lee
    • Communications for Statistical Applications and Methods
    • /
    • v.30 no.2
    • /
    • pp.135-147
    • /
    • 2023
  • Skipped median is more robust than median when outliers are not symmetrically distributed. In this work, we propose a novel algorithm to estimate the skipped median. The idea of skipped median and the new algorithm are extended to regression problem, which is called least clipped absolute deviation (LCAD). Since our proposed algorithm for nonconvex LCAD optimization makes use of convex least absolute deviation (LAD) procedure as a subroutine, regularizations developed for LAD can be directly applied, without modification, to LCAD as well. Numerical studies demonstrate that skipped median and LCAD are useful and outperform their counterparts, median and LAD, when outliers intervene asymmetrically. Some extensions of the idea for skipped median and LCAD are discussed.

More on Quick Analysis of Unreplicated Factorial Designs Avoiding Shrinkage and Inflation Deficiencies

  • Aboukalam, F.
    • International Journal of Reliability and Applications
    • /
    • v.7 no.2
    • /
    • pp.167-175
    • /
    • 2006
  • Effective and quick methods that are easy to carry out even by hand, or easy to be programmed by hand-held calculators are needed for assessing the sizes of contrasts of unreplicated $2^P$ factorial designs. Moreover, they have the advantage to use the original numerical measurements which makes the analysis easier to explain. Basically, Lenth (1989) is one of the most familiar of such quick and powerful methods. Later on, Aboukalam (2001) proposes under constant effects an alternative sophisticated method to Lenth's method. The proposed method is the supreme from two considerable powers. The first utmost indicates less inflation deficiency while the other utmost indicates less shrinkage deficiency. Also under constant effects, Al-Shiha (2006) introduces an alternative quick method which is less shrinkage deficiency while the inflation deficiency is the same. If effects are random, Aboukalam (2005) introduces an alternative quick method in which the first power is favored as long as the second power is within a small margin. In the spirit of quickness and fixed effects, this article adds another method which is supreme from the two considerable powers. The method is based on a one step of the scale-part of a suggested M-estimate for location. Explicitly, we suggest adapting the skipped median (ASKM) estimate. Critical values of ASKM-method, for several sample sizes often used, are empirically computed.

  • PDF

Simultaneous Modulated Accelerated Radiation Therapy and Concurrent Weekly Paclitaxel in the Treatment of Locally Advanced Nasopharyngeal Carcinoma

  • Xie, Cong-Ying;Jin, Xian-Ce;Deng, Xia;Xue, Sheng-Liu;Jing, Zhao;Su, Hua-Fang;Wu, Shi-Xiu
    • Asian Pacific Journal of Cancer Prevention
    • /
    • v.13 no.12
    • /
    • pp.6129-6132
    • /
    • 2012
  • Objectives: To evaluate the feasibility and efficacy of simultaneous accelerated radiation therapy (SMART) and concurrent weekly paclitaxel in the treatment of locally advanced nasopharyngeal carcinoma. Methods: Forty-one patients with pathologically confirmed nasopharyngeal carcinoma were treated by SMART with concurrent weekly paclitaxel. Daily fraction doses of 2.5 Gy and 2.0 Gy were prescribed to the gross tumor volume (GTV) and clinical target volume (CTV) to a total dose of 70 Gy and 56 Gy, respectively. Paclitaxel of $45mg/m^2$ was administered concurrently with radiation therapy every week. Adjuvant chemotherapy was given four weeks after the completion of the radiotherapy (RT) if the tumor demonstrated only a partial response (PR). Results: All patients completed the radiotherapy (RT) course. Adjuvant chemotherapy was administered to 12 patients due to PR. The CR (complete remission) rate was 82.9% three months after RT. Thirty-nine (95.1%) patients completed the concurrent weekly chemotherapy with paclitaxel, and two patients skipped their sixth course. Seven patients had a 15% dosage reduction at the fifth and sixth course due to grade 3 mucositis. The median follow-up was 30 (range, 14-42) months. The three-year overall survival (OS), metastases-free survival (MFS), and local control rates were 77.0%, 64.4%, and 97.6%, respectively. No correlation between survival rate and T or N stage was observed. Grade 3 acute mucositis and xerostomia were present in 17.1% and 7.1%, respectively. Conclusion: SMART with concurrent weekly paclitaxel is a potentially effective and toxicity tolerable approach in the treatment of locally advanced NPC.