Abstract
The methods to minimize AIC or BIC criterion function for selection of regression variables are considered. The main calculations of some of these methods are completed economically and recursively. The methods are shown to be of strong consistency or overconsistency to the true model.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Akaike, H., Statistical Predictor Identification,Ann. Inst. Statist.,22 (1970), 203–217.
Akaike, H., Information Theory and an Extension of the Maximum Likelihood Principle, In 2nd International Symposium on Information Theory, Eds. B. N. Petrov and F. Csaki, 267–281, Budapest: Akademia Kiado, 1973.
Chen G. J., Lai T. L. and Wei C. Z., Convergence System and Strong Consistency of Least Squares Estimates in Regression Models,J. Multivariate Anal.,11 (1981), 319–333.
Lai T. L. and Wei C. Z., A Law of the Iterated Logarithm for Double Arrays of Independent Random Variables with Application to Regression and Time Series Models,Ann. Prob.,10: 2 (1982), 320–335.
Liu C. W. and Wu G. F., Criteria of Variables Selection in Regression Analysis,Mathematics in Practice and Theory,1 (1983), 61–70.
Mallows, C. L., Some Comments onC p ,Technomethics,12 (1973), 591–612.
Schwarz, G., Estimating the Dimension of a Model,Ann. Statist.,6 (1978), 461–464.
Shibata, R., Selection of the Order of an Autoregressive Model by Akaike's Information Criterion,Biometrika,63 (1976), 117–126.
Shibata, R., An Optimal Selection of Regression Variables (to appear inBiometrika).
Zhang R. T. and Fang K. T., Introduction of Multivariate Analysis, Science Press. (in Chinese)
Zhao L. Z., The Necessary and Sufficient Condition for the Estimate of Variance of Error in Linear Model to be of Consistency,Sci. Sinica,10 (1981), 1187–1191.
Additional information
Institute of Applied Mathematics, Academia Sinica
Rights and permissions
About this article
Cite this article
Hongzhi, A., Lan, G. On the selection of regression variables. Acta Mathematicae Applicatae Sinica 2, 27–36 (1985). https://doi.org/10.1007/BF01666516
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01666516