createControl {FamilyRank}

Simulate Control

Description

Numerical feature simulation for negative samples. Called by createData.

Usage

createControl(upper.mean, lower.mean, upper.sd, lower.sd, n.features, 
subtype1.feats = 1:5, subtype2.feats = 6:10, subtype3.feats = 11:15)

Arguments

upper.mean

The mean of the upper component of the bimodal Gaussian distribution from which features are simulated.

lower.mean

The mean of the lower component of the bimodal Gaussian distribution from which features are simulated.

upper.sd

The standard deviation of the upper component of the bimodal Gaussian distribution from which features are simulated.

lower.sd

The standard deviation of the lower component of the bimodal Gaussian distribution from which features are simulated.

n.features

Number of features to simulate.

subtype1.feats

Numeric vector representing the indices of features that define subtype 1.

subtype2.feats

Numeric vector representing the indices of features that define subtype 2.

subtype3.feats

Numeric vector representing the indices of features that define subtype 3.

Details

Simulates data such that none of the 3 subtypes defined in createCase are represented.

To ensure subtype 1 is not represented, at least one of the first three subtype1.feats and/or both of the next 2 subtype1.feats are simulated from the lower component of the Gaussian distribution.

To ensure subtype 2 is not represented, at least one of the five subtype2.feats is simulated from the lower component.

To ensure subtype 3 is not represented, at least one of the first 4 subtype3.feats is simulated from the lower component and/or the last subtype3.feats is simulated from the upper component.

Value

Returns a vector of simulated features

Note

createControl is not meant to be called alone. It is designed as a helper function for createData.

Author(s)

Michelle Saul

References

ADD REFERENCE

See Also

createData

Examples

# Toy Example 
control <- createControl(upper.mean = 13, lower.mean = 5, 
upper.sd = 1, lower.sd = 1, n.features = 20, 
                        subtype1.feats = 1:5,
                        subtype2.feats = 6:10,
                        subtype3.feats = 11:15)