Do any of the BioC demi-gods know how difficult it would be to use nlme's correlation structures: corAR1 autoregressive process of order 1. corARMA autoregressive moving average process, with arbitrary orders for the autoregressive and moving average components. corCAR1 continuous autoregressive process (AR(1) process for a continuous time covariate). corCompSymm compound symmetry structure corresponding to a constant correlation. ...in limma's lmFit as the "correlation=" argument? Thanks in advance, Jake

> Date: Wed, 25 May 2005 20:51:52 -0600 > From: Jacob Michaelson <jjmichael@comcast.net> > Subject: [BioC] using nlme correlation structures in limma? > To: bioconductor@stat.math.ethz.ch > > Do any of the BioC demi-gods know how difficult it would be to use > nlme's correlation structures: > > corAR1 > autoregressive process of order 1. > corARMA > autoregressive moving average process, with arbitrary orders for the > autoregressive and moving average components. > corCAR1 > continuous autoregressive process (AR(1) process for a continuous > time covariate). > corCompSymm > compound symmetry structure corresponding to a constant correlation. > > ...in limma's lmFit as the "correlation=" argument? Are you planning to take this on as a research project, or are you asking about how the software works? If the later, this is not possible. You can be sure it would be mentioned in the document it it was. Gordon > Thanks in advance, > > Jake