cvrelaxo               package:relaxo               R Documentation

_C_r_o_s_s _v_a_l_i_d_a_t_i_o_n _f_o_r "_R_e_l_a_x_e_d _L_a_s_s_o"

_D_e_s_c_r_i_p_t_i_o_n:

     Compute the "Relaxed Lasso" solution with minimal cross-validated
     L2-loss.

_U_s_a_g_e:

     cvrelaxo(X, Y, K = 5, phi = seq(0, 1, length = 10), max.steps = min( 2* length(Y), 2 * ncol(X)), fast = TRUE, keep.data = TRUE, warn=TRUE)

_A_r_g_u_m_e_n_t_s:

       X: as in function 'relaxo' 

       Y: as in function 'relaxo' 

       K: Number of folds. Defaults to 5. 

     phi: as in function 'relaxo' 

max.steps: as in function 'relaxo' 

    fast: as in function 'relaxo' 

keep.data: as in function 'relaxo' 

    warn: as in function 'relaxo' 

_D_e_t_a_i_l_s:

     The plot method is not useful for result of 'cvrelaxo' (as no path
     of solutions exists).

_V_a_l_u_e:

     An object of class 'relaxo', for which print and predict methods
     exist

_A_u_t_h_o_r(_s):

     Nicolai Meinshausen nicolai@stat.berkeley.edu

_R_e_f_e_r_e_n_c_e_s:

     N. Meinshausen, "Relaxed Lasso", Computational Statistics and Data
     Analysis, to appear. <URL: http://www.stat.berkeley.edu/~nicolai>

_S_e_e _A_l_s_o:

     See also 'relaxo' for computation of the entire solution path

_E_x_a_m_p_l_e_s:

             data(diabetes)

     ## Center and scale variables
             x <- scale(diabetes$x)
             y <- scale(diabetes$y)
             
     ## Compute "Relaxed Lasso" solution and plot results
             object <- relaxo(x,y)
             plot(object)   
             
     ## Compute cross-validated solution with optimal 
     ## predictive performance and print relaxation parameter phi and 
     ## penalty parameter lambda of the found solution
             cvobject <- cvrelaxo(x,y)
             print(cvobject$phi)
             print(cvobject$lambda)
             
     ## Compute fitted values and plot them versus actual values     
             fitted.values <- predict(cvobject)
             plot(fitted.values,y)
             abline(c(0,1))

