Predict from a fitted cv.bridge object

Compute response predictions, extract coefficients, or identify nonzero predictors from a fitted cv.bridge object.

Usage

# S3 method for class 'cv.bridge'
predict(
  object,
  newx,
  s = c("lambda.min", "lambda.1se"),
  type = c("response", "nonzero", "coefficients"),
  ...
)

Arguments

object

Fitted object returned by cv.bridge, with p predictors in its training design.

newx

Numeric matrix with one row per new observation and the same p columns, in the same order, as the training design. A numeric vector of length p represents one observation. Values are supplied on the original predictor scale. Required only for type = "response".

s

Penalty selection, using numeric fitted values or a character name. Numeric values must match object$lambda exactly; no interpolation is used. The character selectors are:

"lambda.min": Select the penalty with minimum CV error.
"lambda.1se": Select using the historical CV error bars.

The default is lambda.min.

type

Output to return: "response" for fitted response values, "coefficients" for intercept and slopes, or "nonzero" for predictor indices over the entire fitted path.

...

Additional arguments accepted for compatibility.

Value

For type = "response", a numeric vector for one selected penalty or a matrix with one row per new observation and one column per selected penalty. For type = "coefficients", a numeric matrix with p + 1 rows, including the intercept, even for one penalty. For type = "nonzero", a pathwise collection of 1-based predictor indices excluding the intercept. Its historical container can simplify depending on the support pattern and number of predictors.

Details

Prediction uses the fitted intercept and original-scale slopes. Columns of newx are matched by position, not reordered by their names. For type = "nonzero", all fitted penalties are inspected and s does not restrict the returned indices. The defaults differ between coef() and predict(): coefficient extraction uses lambda.1se, whereas response prediction uses lambda.min. Specify the same s in both calls when comparing coefficients and their predictions.

Author

Bahadir Yuzbasi
Maintainer: Bahadir Yuzbasi b.yzb@hotmail.com

Examples

# Reproducible synthetic demonstration: 100 observations, eight predictors.
set.seed(2019)
beta <- c(3, 1.5, 0, 0, 2, 0, 0, 0)
p <- length(beta)
beta <- matrix(beta, nrow = p, ncol = 1)
n <- 100
X <- matrix(rnorm(n * p), nrow = n, ncol = p)
y <- as.numeric(X %*% beta + rnorm(n))

# Five penalties keep this help example fast; the default is 100.
model1 <- cv.bridge(X, y, q = 1, nlambda = 5,
                     nfolds = 3, num_threads = 1)
# Predict five observations at one explicitly selected penalty.
predict(model1, newx = X[1:5, , drop = FALSE], s = "lambda.min")
#> [1]  -1.4546979   0.3068586  -1.5652478   2.6580196 -10.4100022
# Extract coefficients using the complete type name.
predict(model1, s = "lambda.min", type = "coefficients")
#>                   0.001
#> (Intercept)  0.02436200
#> V1           2.97264933
#> V2           1.57302384
#> V3           0.07468856
#> V4          -0.08748886
#> V5           1.98528242
#> V6          -0.09864804
#> V7           0.07149838
#> V8          -0.02593340
# Predictor indices for every fitted penalty; the intercept is excluded.
predict(model1, type = "nonzero")
#> $`802.149726533951`
#> [1] 1 5
#> 
#> $`26.8035044402758`
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $`0.895628118436414`
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $`0.0299270466039737`
#> [1] 1 2 3 4 5 6 7 8
#> 
#> $`0.001`
#> [1] 1 2 3 4 5 6 7 8
#>