Relative importance rankings outperform marginal correlation for variable ranking and yield competitive predictive models versus lasso in simulations and high-dimensional gene data, with a new efficient RI measure CRI.Z.
Efroymson, Stepwise regression–a backward and forward look, in: Eastern Regional Meetings of the Institute of Mathematical Statistics, 1966
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Variable Selection Using Relative Importance Rankings
Relative importance rankings outperform marginal correlation for variable ranking and yield competitive predictive models versus lasso in simulations and high-dimensional gene data, with a new efficient RI measure CRI.Z.