A new statistical approach to combining p-values using gamma distribution and its application to genome-wide association study

被引:27
作者
Chen, Zhongxue [1 ]
Yang, William [2 ]
Liu, Qingzhong [3 ]
Yang, Jack Y. [4 ,5 ,6 ]
Li, Jing [1 ]
Yang, Mary Qu [7 ,8 ,9 ]
机构
[1] Indiana Univ, Sch Publ Hlth, Dept Epidemiol & Biostat, Bloomington, IN 47405 USA
[2] Univ Arkansas, Dept Comp Sci, George W Donaghey Coll Engn & Informat Technol, Little Rock, AR 72204 USA
[3] Sam Houston State Univ, Dept Comp Sci, Huntsville, TX 77341 USA
[4] Indiana Univ Sch Med, Ctr Compuat Biol & Bioinformat, Indianapolis, IN 46202 USA
[5] Massachusetts Gen Hosp, Div Biostat & Biomath, Boston, MA 02114 USA
[6] Harvard Univ, Sch Med, Boston, MA 02114 USA
[7] Univ Arkansas, George W Donaghey Coll Engn & Informat Technol, Dept Informat Sci, MidSouth Bioinformat Ctr, Little Rock, AR 72204 USA
[8] Univ Arkansas, Joint Bioinformat Grad Program, Little Rock, AR 72204 USA
[9] Univ Arkansas Med Sci, Little Rock, AR 72204 USA
来源
BMC BIOINFORMATICS | 2014年 / 15卷
基金
美国国家卫生研究院;
关键词
DIFFERENTIALLY METHYLATED LOCI; WEIGHTED Z-TEST; INDEPENDENT TESTS; MULTIPLE DISEASES; PROBABILITIES; COMBINATION;
D O I
10.1186/1471-2105-15-S17-S3
中图分类号
Q5 [生物化学];
学科分类号
071010 ; 081704 ;
摘要
Background: Combining information from different studies is an important and useful practice in bioinformatics, including genome-wide association study, rare variant data analysis and other set-based analyses. Many statistical methods have been proposed to combine p-values from independent studies. However, it is known that there is no uniformly most powerful test under all conditions; therefore, finding a powerful test in specific situation is important and desirable. Results: In this paper, we propose a new statistical approach to combining p-values based on gamma distribution, which uses the inverse of the p-value as the shape parameter in the gamma distribution. Conclusions: Simulation study and real data application demonstrate that the proposed method has good performance under some situations.
引用
收藏
页数:7
相关论文
共 29 条
  • [1] [Anonymous], 1932, STAT METHODS RES WOR
  • [2] [Anonymous], 1949, THE AM SOLDIER
  • [3] COMBINING INDEPENDENT TESTS OF SIGNIFICANCE
    BIRNBAUM, A
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1954, 49 (267) : 559 - 574
  • [4] An Exponential Combination Procedure for Set-Based Association Tests in Sequencing Studies
    Chen, Lin S.
    Hsu, Li
    Gamazon, Eric R.
    Cox, Nancy J.
    Nicolae, Dan L.
    [J]. AMERICAN JOURNAL OF HUMAN GENETICS, 2012, 91 (06) : 977 - 986
  • [5] Is the weighted z-test the best method for combining probabilities from independent tests?
    Chen, Z.
    [J]. JOURNAL OF EVOLUTIONARY BIOLOGY, 2011, 24 (04) : 926 - 930
  • [6] Chen Z, 2013, TESTING ASS CASE CON, DOI 101177/09622802124740612013
  • [7] Chen Z, 2014, DETECTING ASS SINGLE, DOI 2010.1177/0962280214551815.
  • [8] Design and analysis of multiple diseases genome-wide association studies without controls
    Chen, Zhohgxue
    Huang, Hanwen
    Ng, Hon Keung Tony
    [J]. GENE, 2012, 510 (01) : 87 - 92
  • [9] An improved robust association test for GWAS with multiple diseases
    Chen, Zhongxue
    Huang, Hanwen
    Ng, Hon Keung Tony
    [J]. STATISTICS & PROBABILITY LETTERS, 2014, 91 : 153 - 161
  • [10] A new association test based on disease allele selection for case-control genome-wide association studies
    Chen, Zhongxue
    [J]. BMC GENOMICS, 2014, 15