
Last chance! 50% off unlimited learning
Sale ends in
tmlenet
tmlenet
package
tmlenet_options(useglm = FALSE, parfit = FALSE, bin.method = c("equal.len", "equal.mass", "dhist"), nbins = NA, maxncats = 20, poolContinVar = FALSE, maxNperBin = 1000)
FALSE
to estimate with speedglm.wfit
and TRUE
for
glm.fit
.FALSE
. Set to TRUE
to use foreach
package and its functions
foreach
and dopar
to perform
parallel logistic regression fits and predictions for discretized continuous outcomes. This functionality
requires registering a parallel backend prior to running tmlenet
function, e.g.,
using doParallel
R package and running registerDoParallel(cores = ncores)
for integer
ncores
parallel jobs. For an example, see a test in "./tests/RUnit/RUnit_tests_04_netcont_sA_tests.R".sA
. The default method is "equal.len"
, which partitions the range of sA
into equal length nbins
intervals. Method "equal.mass"
results in a data-adaptive selection of the bins
based on equal mass (equal number of observations), i.e., each bin is defined so that it contains an approximately
the same number of observations across all bins. The maximum number of observations in each bin is controlled
by parameter maxNperBin
. Method "dhist"
uses a mix of the above two approaches,
see Denby and Mallows "Variations on the Histogram" (2009) for more detail.bin.method = "equal.len"
.
If left as NA
the total number of equal intervals (bins) is determined by the nearest integer of
nobs
/maxNperBin
, where nobs
is the total number of observations in the input data.sA[j]
can have.
If sA[j]
has more it is automatically considered continuous.TRUE
for fitting a pooled regression which pools bin indicators across all bins.
When fitting a model for binirized continuous outcome, set to TRUE
for pooling bin indicators across several bins into one outcome regression?bin.method="equal.mass"
and indirectly when bin.method="equal.len"
, but nbins = NA
).print_tmlenet_opts