Multiple testing and simultaneous confidence intervals: Calculation of constants

    Authors

    P. N. Somerville

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Comput. Stat. Data Anal.

    Keywords

    multiple testing; multiple comparisons; simultaneous confidence; intervals; multivariate integral; Monte Carlo; numerical integration; interactive computing; Computer Science, Interdisciplinary Applications; Statistics &; Probability

    Abstract

    A methodology has been developed which makes it possible to calculate efficiently, in an interactive mode, the constants required for a large class of multiple hypotheses tests and simultaneous confidence interval estimates. The method is a mixture of Monte Carlo and numerical integration, taking into account the special structure of the (acceptance) regions. An interactive Fortran 90 program, QINTER2, and a batch program QBATCH2 have been written to implement the methodology. Sample results are given. (C) 1997 Elsevier Science B.V.

    Journal Title

    Computational Statistics & Data Analysis

    Volume

    25

    Issue/Number

    2

    Publication Date

    1-1-1997

    Document Type

    Article

    Language

    English

    First Page

    217

    Last Page

    233

    WOS Identifier

    WOS:A1997XN78300007

    ISSN

    0167-9473

    Share

    COinS