Conditional p-values for the F-statistic in a forward selection procedure

DOI10.1016/0167-9473(94)00047-MzbMath0875.62079OpenAlexW2023744006MaRDI QIDQ672522

Eugene Grechanovsky, Ilia Pinsker

Publication date: 28 February 1997

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-9473(94)00047-m

zbMATH Keywords

Monte CarloRegressionVariable selectionConditioning on the pastMultidimensional integralsStepwise significance testing

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Linear inference, regression (62J99) Probabilistic methods, stochastic differential equations (65C99)

Related Items

Adjusting Stepwisep-Values in Generalized Linear Models ⋮ Applied regression analysis bibliography update 1994-97

Uses Software

• nlr
• AS 195
• Algorithm 725

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Algorithm AS 251: Multivariate Normal Probability Integrals with Product Correlation Structure
• Algorithm AS 195: Multivariate Normal Probabilities with Error Bound
• The Significance Attained by the Best-Fitting Regressor Variable
• Selection of Subsets of Regression Variables
• The use of conditional cutoffs in a forward selection procedure
• Bounds on theP-value of the best fitting regressor variable calculated to a prespecified accuracy
• Selection of Variables in Multiple Regression: Part II. Chosen Procedures, Computations and Examples
• Actual rejection levels in a certain stepwise test
• The Little Bootstrap and Other Methods for Dimensionality Selection in Regression: X-Fixed Prediction Error
• A Biometrics Invited Paper. The Analysis and Selection of Variables in Linear Regression
• Algorithm 717: Subroutines for maximum likelihood and quasi-likelihood estimation of parameters in nonlinear regression models
• Corrigendum
• The distribution of certain regression statistics
• A Stopping Rule for Variable Selection in Multiple Regression
• The Use of an F-Statistic in Stepwise Regression Procedures