Compute Cochran's Q statistic for testing whether the a fixed effects or
a random effects model will be appropriate.
Usage
f.Q(dadj, varadj)
Arguments
dadj
A matrix, each row is a gene, each column a study, of the
estimated t-statistics.
varadj
A matrix, each row is a gene, each column a study, of
the estimated, adjusted variances of the t-statistics.
Value
A vector of length equal to the number of rows of dadj with the
Q statistics.
Details
A straightforward computation of Cochran's Q statistic. If the null
hypothesis that the data are well modeled by a fixed effects design is
true then the estimate Q values will have approximately a chi-squared
distribution with degrees of freedom equal to the number of studies
minus one.
References
Choi et al, Combining multiple microarray studies and
modeling interstudy variation. Bioinformatics, 2003, i84-i90.