invvar function

Inverse Method Variances

Estimate the features' variances using the inverse method. This function is usually called from RUVinv and not normally intended for stand-alone use.

invvar(Y, ctl, XZ = NULL, eta = NULL, lambda = NULL,
       invsvd = NULL)

Arguments

• Y: The data. A m by n matrix, where m is the number of samples and n is the number of features.
• ctl: The negative controls. A logical vector of length n.
• XZ: A m by (p + q) matrix containing both the factor(s) of interest (X) and known covariates (Z).
• eta: Gene-wise (as opposed to sample-wise) covariates. These covariates are adjusted for by RUV-1 before any further analysis proceeds. A matrix with n columns.
• lambda: Ridge parameter. If specified, the ridged inverse method will be used.
• invsvd: Can be included to speed up execution. Generally used when calling invvar many times with different values of lambda.

Returns

A list containing - sigma2: Estimates of the features' variances. A vector of length n.

• df: The "effective degrees of freedom"

• invsvd: Can be used to speed up future calls of invvar.

References

Removing Unwanted Variation from High Dimensional Data with Negative Controls. Gagnon-Bartsch, Jacob, and Speed, 2013. Available at: http://statistics.berkeley.edu/tech-reports/820.

Author(s)

Johann Gagnon-Bartsch johanngb@umich.edu

See Also

RUVinv, RUVrinv