odm.control: Control tuning parameters for "OutlierDM" object
In OutlierDM: Outlier Detection for Multi-replicated High-throughput Data

Description Usage Arguments See Also

various parameters that control aspects of the "OutlierDM" object

odm.control(pair.cre = 1, dist.mthd = "median", 
  Lower = .25, Upper = .75, trans = "log2", 
  centering = TRUE, projection.type = "PCA", lbda = 1, 
  nonlin.method = "L-BFGS-B", nonlin.SS = "AsymOff", 
  nonlin.Frank = c(2, -8, 0, 1), ncl = 2, alpha = 0.05 )

`pair.cre`	a scalar parameter to specify the minimum number of pairs, used in "type = pair".
`dist.mthd`	a distance parameter used in "type = diff". you can choose one of "median", "mean" or and so on.
`Lower`	a criterion for lower quantile value used to construct boxplot
`Upper`	a criterion for upper quantile value used to construct boxplot
`trans`	a parameter for a logarithm and exponential transformation. If a log 2 transformation is needed, set "trans = log2". If no transformation is needed, set "trans = FALSE".
`centering`	a logical parameter for the status of centering. If "centering = TRUE", data are centered by its column means.
`projection.type`	a parameter to determine a type of projection methods. Choose one of "naive", "pca", and "robust".
`lbda`	a criterion about lambda used for nonlinear quantile regression.
`nonlin.method`	a parameter to determine a type of methods used for nonlinear quantile regression. choose one of "L-BFGS-B" and "BFGS". Default is "L-BFGS-B".
`nonlin.SS`	a parameter to determine a type of structure used for nonlinear quantile regression. choose one of "Frank", "Self", "Asym" and "AsymOff". Default is "AsymOff", Asymptotic Regression Model with an Offset.
`nonlin.Frank`	a structure parameter used for Frank copula model. Gain c(df, delta, mu, sigma) in the Frank copula formula
`ncl`	A parameter to determine the number of cores used in parallel computing. A default value is 2.
`alpha`	A sigfinicance level of the Grubbs test. A default value is 0.05.