lasso2 (version 1.2-2)

summary.l1ce: Summary Method for ``l1ce'' Objects (Regression with L1 Constraint)

Description

Returns a summary list for a regression model with an L1 constraint on the parameters. A null value will be returned if printing is invoked.

Usage

## S3 method for class 'l1ce':
summary(object, correlation = TRUE,
         type = c("OPT", "Tibshirani"),
         gen.inverse.diag = 0, sigma = NULL, ...)
## S3 method for class 'summary.l1ce':
print(x, digits = max(3, getOption("digits") - 3), ...)

Value

an object of class summary.l1ce (for which there's a print method). It is basically a list with the following components:correlationthe computed correlation coefficient matrix for the coefficients in the model.cov.unscaledthe unscaled covariance matrix; i.e, a matrix such that multiplying it by an estimate of the error variance produces an estimated covariance matrix for the coefficients.dfthe number of degrees of freedom for the model and for residuals.coefficientsa matrix with three columns, containing the coefficients, their standard errors and the corresponding t statistic.residualsthe model residuals. These are the weighted residuals if weights were given in the model.sigmathe residual standard error estimate.termsthe terms object used in fitting this model.callthe call object used in fitting this model.boundthe bound used in fitting this model.relative.boundthe relative bound used in fitting this model (may not be present).Lagrangianthe Lagrangian of the model.

Details

This function is a method for the generic function summary() for class "l1ce". It can be invoked by calling summary(x) for an object x of the appropriate class, or directly by calling summary.l1ce(x) regardless of the class of the object.

See Also

l1ce, l1ce.object, summary.

Examples

data(Prostate)
summary(l1ce(lpsa ~ .,Prostate))

# Produces the following output:
Call:
 l1ce(formula = lpsa ~ ., data = Prostate)
Residuals:
    Min      1Q Median    3Q  Max
 -1.636 -0.4119  0.076 0.452 1.83


Coefficients:
             Value Std. Error Z score Pr(>|Z|)
(Intercept) 0.7285 1.3898     0.5242  0.6002
     lcavol 0.4937 0.0919     5.3711  0.0000
    lweight 0.2682 0.1774     1.5115  0.1307
        age 0.0000 0.0111     0.0000  1.0000
       lbph 0.0093 0.0587     0.1581  0.8744
        svi 0.4551 0.2525     1.8023  0.0715
        lcp 0.0000 0.0947     0.0000  1.0000
    gleason 0.0000 0.1685     0.0000  1.0000
      pgg45 0.0002 0.0046     0.0391  0.9688


Residual standard error: 0.7595 on 88.36 degrees of freedom
The relative L1 bound was      : 0.5
The absolute L1 bound was      : 0.9219925
The Lagrangian for the bound is:  13.05806


Correlation of Coefficients:
        (Intercept)  lcavol lweight     age    lbph     svi     lcp gleason
 lcavol  0.1988
lweight -0.4815     -0.2071
    age -0.3938     -0.0603 -0.0974
   lbph  0.3629     -0.0201 -0.5165 -0.1303
    svi -0.0624     -0.2273 -0.1442  0.0635  0.0648
    lcp  0.0457     -0.4153  0.0598  0.0665  0.0632 -0.3779
gleason -0.7666     -0.2009  0.1163 -0.0774 -0.0617  0.1084 -0.0243
  pgg45  0.4988      0.0956 -0.0380 -0.0630 -0.1111 -0.1921 -0.2935 -0.6526