staged.blocks {LGDtoolkit} | R Documentation |
Staged blocks regression
Description
staged.blocks
performs blockwise regression where the predictions of each blocks' model is used as an
offset for the model of the following block.
Usage
staged.blocks(method, target, db, blocks, reg.type = "ols", p.value = 0.05)
Arguments
method |
Regression method applied on each block.
Available methods: |
target |
Name of target variable within |
db |
Modeling data with risk factors and target variable. |
blocks |
Data frame with defined risk factor groups. It has to contain the following columns: |
reg.type |
Regression type. Available options are: |
p.value |
Significance level of p-value for the estimated coefficient. For numerical risk factors this value is
is directly compared to p-value of the estimated coefficient, while for categorical
multiple Wald test is employed and its p-value is used for comparison with selected threshold ( |
Value
The command staged.blocks
returns a list of three objects.
The first object (model
) is the list of the models of each block (an object of class inheriting from "lm"
).
The second object (steps
), is the data frame with risk factors selected from the each block.
The third object (dev.db
), returns the list of block's model development databases.
See Also
embedded.blocks
, ensemble.blocks
, stepFWD
and stepRPC
.
Examples
library(LGDtoolkit)
data(lgd.ds.c)
#stepwise with continuous risk factors
set.seed(123)
blocks <- data.frame(rf = names(lgd.ds.c)[!names(lgd.ds.c)%in%"lgd"],
block = sample(1:3, ncol(lgd.ds.c) - 1, rep = TRUE))
blocks <- blocks[order(blocks$block, blocks$rf), ]
res <- LGDtoolkit::staged.blocks(method = "stepFWD",
target = "lgd",
db = lgd.ds.c,
reg.type = "ols",
blocks = blocks,
p.value = 0.05)
names(res)
res$models
summary(res$models[[3]])
identical(unname(predict(res$models[[1]], newdata = res$dev.db[[1]])),
res$dev.db[[2]]$offset.vals)