Alternative regression methods are not considered in Murtaugh (2009) or by ecologists in general.

Murtaugh (2009) recently illustrated that all subsets variable selection is very similar to stepwise regression. This, however, does not necessarily mean both methods are useful. On the contrary, the same problems with overfitting should apply. Ecologists should, if model building is indeed necessary, consider more reliable regression methods now available.

[1]  R. Tibshirani,et al.  Covariance‐regularized regression and classification for high dimensional problems , 2009, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[2]  J. Copas.  Regression, Prediction and Shrinkage , 1983 .

[3]  J. Goeman.  L1 Penalized Estimation in the Cox Proportional Hazards Model , 2009, Biometrical journal. Biometrische Zeitschrift.

[4]  V. Flack,et al.  Frequency of Selecting Noise Variables in Subset Regression Analysis: A Simulation Study , 1987 .

[5]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[6]  Clifford M. Hurvich,et al.  The impact of model selection on inference in linear regression , 1990 .

[7]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[8]  R. O’Hara,et al.  A review of Bayesian variable selection methods: what, how and which , 2009 .

[9]  Roger Mundry,et al.  Stepwise Model Fitting and Statistical Inference: Turning Noise into Signal Pollution , 2008, The American Naturalist.

[10]  E. Niclas Jonsson,et al.  The lasso—a novel method for predictive covariate model building in nonlinear mixed effects models , 2007, Journal of Pharmacokinetics and Pharmacodynamics.

[11]  P. Royston,et al.  Selection of important variables and determination of functional form for continuous predictors in multivariable model building , 2007, Statistics in medicine.

[12]  Paul A Murtaugh,et al.  Performance of several variable-selection methods applied to real ecological data. , 2009, Ecology letters.