corParams {Envisage} | R Documentation |
Flags all highly correlated variables which model the same data to reduce the number of variables and interactions in the model calculation.
corParams(pData)
pData |
An object of class
phenoData containing the
phenotypic information for the experiment. |
The Envisage package contains methods allowing the use of linear models (LMs) for analysing significantly changing genes in experiments with a variety of sources of variation, be they experimentally controlled variables such as drug treatment or time, or non-controlled sources of confounding variation such as phenotypic or environmental differences. This allows all sources of variation to be considered when analysing for significant differential expression, ensuring resulting genes are biologically relevent to the experimental question.
The function corParams
identifies variables
within the study design that are highly correlated and flags
them up for the user. These may represent different representations of
the same data and will affect model fitting, so should be removed from
the data set. Variables found to be highly correlated are suffixed
with the flags '*', '**', '***' etc.
corParams
is an internal function and is not
designed to be accessed by users.
A list is returned containing the following slots:
corParamNames |
A character vector of the names of the parameters found to have very high correlation, suffixed with flags '*', '**', '***' etc. |
corParams |
A list containing the indices for variables found to be highly correlated with one another. |
Sam Robson S.C.Robson@warwick.ac.uk
Robson, S. C., Hunter, E., Bird, H., Turner, H. (2008) Envisage: model-based significance analysis of microarray gene expression data, manuscript in preparation
For the main Envisage method, see
envisage
.