发明名称 TECHNIQUES TO SIMULATE STATISTICAL TESTS
摘要 Techniques to simulate statistical tests are described. An apparatus may comprise a simulated data component to generate simulated data for a statistical test, where statistics of the statistical test are based on parameter vectors to follow a probability distribution, a statistic simulator component to generate statistics for the parameter vectors from the simulated data, each parameter vector represented with a single point in a grid of points, the statistic simulation component to distribute portions of the simulated data or simulated statistics across multiple nodes of a distributed computing system in accordance with a column-wise or column-wise-by-group distribution algorithm, and a code generator component to create a computational representation arranged to generate an approximate probability distribution for each point in the grid of points from the simulated statistics, the approximate probability distribution to comprise an empirical cumulative distribution function (CDF). Other embodiments are described and claimed.
申请公布号 US2014330536(A1) 申请公布日期 2014.11.06
申请号 US201414270662 申请日期 2014.05.06
申请人 Chen Xilong;Little Mark Roland 发明人 Chen Xilong;Little Mark Roland
分类号 G06F17/18 主分类号 G06F17/18
代理机构 代理人
主权项 1. An article of manufacture comprising a non-transitory computer-readable storage medium containing instructions that, when executed, enable a system to: generate simulated data for a statistical test, where statistics of the statistical test are based on parameter vectors to follow a probability distribution; generate statistics for the parameter vectors from the simulated data, each parameter vector represented with a single point in a grid of points used for interpolation, with a distributed computing system comprising multiple nodes each having one or more processors capable of executing multiple threads, the simulation to occur through distribution of portions of the simulated data or simulated statistics across the multiple nodes of the distributed computing system in accordance with at least one of a column-wise distribution algorithm or column-wise-by-group distribution algorithm; and create a computational representation arranged to generate an approximate probability distribution for each point in the grid of points from the simulated statistics, the approximate probability distribution to comprise an empirical cumulative distribution function (CDF).
地址 Chapel Hill NC US