BinaryLogBiplotGD function

Binary Logistic Biplot with Gradient Descent Estimation

Binary Logistic Biplot with Gradient Descent Estimation. An external optimization function is used to calculate the parameters.

BinaryLogBiplotGD(X, freq = matrix(1, nrow(X), 1), dim = 2, tolerance =
                   1e-07, penalization = 0.01, num_max_iters = 100,
                   RotVarimax = FALSE, seed = 0, OptimMethod = "CG",
                   Initial = "random", Orthogonalize = FALSE, Algorithm =
                   "Joint", ...)

Arguments

• X: A binary data matrix
• freq: Frequencies of each row. When adequate.
• dim: Dimension of the final solution.
• tolerance: Tolerance for convergence of the algorithm.
• penalization: Ridge penalization constant.
• num_max_iters: Maximum number of iterations of the algorithm.
• RotVarimax: Should the final solution be rotated.
• seed: Seed for the random numbers. Used for reproductibility.
• OptimMethod: Optimization method used by optim.
• Initial: Initial configuration to start the iterations.
• Orthogonalize: Should te solution be orthogonalized?.
• Algorithm: Algorithm for esimation: Joint or alternated.
• ...: Aditional parameters used by the optimization function.

Details

Fits a binary logistic biplot using gradient descent. The general function optim is used to optimize the loss function. Conjugate gradien is used as a default although other alternatives can be USED.

Returns

An object of class "Binary.Logistic.Biplot".

References

Vicente-Villardon, J. L., Galindo, M. P. and Blazquez, A. (2006) Logistic Biplots. In Multiple Correspondence Análisis And Related Methods. Grenacre, M & Blasius, J, Eds, Chapman and Hall, Boca Raton.

Demey, J., Vicente-Villardon, J. L., Galindo, M.P. AND Zambrano, A. (2008) Identifying Molecular Markers Associated With Classification Of Genotypes Using External Logistic Biplots. Bioinformatics, 24(24): 2832-2838.

Author(s)

Jose Luis Vicente-Villardon

Examples

data(spiders)
X=Dataframe2BinaryMatrix(spiders)

logbip=BinaryLogBiplotGD(X,penalization=0.1)
plot(logbip, Mode="a")
summary(logbip)