BTLLasso (version 0.1-1)

BTLLasso.ctrl: Control function for BTLLasso

Description

Contains some additional parameters, mostly for internal use.

Usage

BTLLasso.ctrl(adaptive = TRUE, norm = c("L1", "L2"), epsilon = 1e-04, lambda2 = 1e-04, 
              c = 1e-09, penal.diffs = TRUE,return.design = TRUE)

Arguments

adaptive

Should adaptive lasso be used? Default is TRUE.

norm

Specifies the norm used in the penalty term. Currently, only "L1" and "L2" are possible. Default is to "L1", only "L1" allows for clustering and variable selection.

epsilon

Threshold value for convergence of the algorithm.

lambda2

Tuning parameter for ridge penalty on all coefficients. Should be small, only used to stabilize results.

c

Internal parameter for the quadratic approximation of the L1 penalty. Should be sufficiently small. For details see cat_control.

penal.diffs

Should also differences between all parameters be penalized? Default is TRUE. If FALSE, only absolute values are penalized.

return.design

Should the design matrix be returned from the BTLLasso function. Necessary for internal use.

References

Schauberger, Gunther and Tutz, Gerhard (2015): Modelling Heterogeneity in Paired Comparison Data - an L1 Penalty Approach with an Application to Party Preference Data, Department of Statistics, LMU Munich, Technical Report 183

See Also

BTLLasso, cv.BTLLasso

Examples

# load data set
data(GLESsmall)

# define response and covariate matrix
X <- scale(GLESsmall[, 11:14])
Y <- as.matrix(GLESsmall[, 1:10])

# vector of subtitles, containing the coding of the single covariates
subs <- c("(in years)","female (1); male (0)",
"East Germany (1); West Germany (0)","(very) good (1); else (0)")

# vector of tuning parameters
lambda <- exp(seq(log(31),log(1),length=50))-1

# compute BTLLasso model, increase accuracy of the algorithm
m <- BTLLasso(Y = Y, X = X, lambda = lambda, control = BTLLasso.ctrl(epsilon = 1e-05))