Regressions by Leaps and Bounds

By G. M. Furnival, R. Wilson. 2000

724 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

Citations in the corpus

Extended Comparisons of Best Subset Selection, Forward Stepwise Selection, and the Lasso (2017, neutral): “…many years has been that this problem is not solveable beyond (say) p in the 30s, this view being shaped by the available software for best subset selection (e.g., in the R language, the leaps package implements a branch-and-bound algorithm for best subset selection of Furnival and Wilson, 1974).”
Weighted‐Average Least Squares (WALS): A Survey (2016, methodology): “The subset of models to be investigated can be identified either by deterministic search methods such as Occam’s window (Madigan and Raftery, 1994) and the leaps and bounds algorithm (Furnival and Wilson, 1974), or by stochastic search methods based on Markov chain Monte Carlo (MCMC) techniques; see”
Bayesian Adaptive Sampling for Variable Selection and Model Averaging (2011, background): “Key Words: Bayesian model averaging; Inclusion probability; Markov chain Monte Carlo; Median probability model; Model uncertainty; Sampling without replacement.”
Comparison of machine learning and traditional classifiers in glaucoma diagnosis (2002, methodology): “We are TABLE II p-VALUES FOR THE TWO–TAILS TEST BETWEEN ROC AREAS OF THE STATPAC PSD INDEX AND THE MACHINE-LEARNING CLASSIFIERS TABLE III p-VALUES FOR TWO-TAILS TEST BETWEEN ROC AREAS OF THE DISCRIMINATIVE CLASSIFIERS TABLE IV p-VALUE FOR THE TWO-TAILS TEST BETWEEN ROC AREAS OF THE GENERATIVE CLASSI”
Model Averaging in Economics: An Overview (2015, neutral): “Therefore, using an appropriate search strategy (for instance the leaps and bounds algorithm by Furnival and Wilson (1974)) the number of models to be estimated is drastically reduced. Madigan and Raftery (1994) provide a detailed description of the method. Another commonly-used alternative, initial”
Variable selection with stepwise and best subset approaches. (2016, methodology): “This approach has been in use for linear regression for several decades with the branch and bound algorithm (6).”
The Practical Implementation of Bayesian Model Selection (2001, methodology): “This approach has worked well in moderate sized problems, where leaps and bounds (Furnival and Wilson 1974) was used to select a subset of models; these were then used to construct the EB prior distribution, and then estimates under BMA with the estimated prior.”
Applied Linear Regression (2004, methodology): “For p ≤ 30, the leaps and bounds algorithm (Furnival et al., 1974) can be used to find the few candidate models that minimize aic or bic without actually computing all possible models.”
Model Averaging and Its Use in Economics (2017, methodology): “George (2010) suggests three distinct approaches for the construction of these so-called “dilution priors”, based on tessellation determined neighbourhoods, collinearity adjustments, and pairwise distances between models.”
Methods and Criteria for Model Selection (2004, methodology): “This approach, even with advances in computing power and memory, as well as the development of algorithms that allow the user to avoid calculating most of the models (for instance, Furnival and Wilson 1974), is most feasible when the number of variables is moderate.”
Bayesian model averaging: development of an improved multi-class, gene selection and classification tool for microarray data (2005, methodology): “In order to efﬁciently compute a reduced set of good models, we use the leaps and bounds algorithm (Furnival and Wilson, 1974), which returns the best ‘nbest’ models for each size up to 30 variables.”
Algorithm for cardinality-constrained quadratic optimization (2009, background): “Authors of [2, 9, 10] use pivoting and enumeration to search for subsets with the best regression “fit” (e.”