A New Estimator of Significance of Correlation in Time Series Data

 

Semyon Kruglyak  Haixu Tang

Department of Mathematics

University of Southern California,

Los Angeles, CA90089

(J. Comp. Biol., to be published)

 

Abstract

 

Many expression array experiments monitor gene activity as an organism goes through some biological process. It is desirable to find genes with similar expression patterns in the resulting time series data.We propose a new simulation approach that assesses the statistical significance of similarity scores between expression patterns. The simulation takes into account the dependence between columns of data. Download fulltext paper (gzipped ps format).