Abstract
Information criteria are used in many applications including statistical model selection and intelligent systems. The traditional information criteria such as the Akaike information criterion (AIC) do not always provide an adequate penalty on the number of model covariates. To address this issue, we propose a novel method for evaluating statistical models based on information criterion. The proposed method, called regularized information criterion (RIL), modifies the penalty term in AIC to reduce model overfitting. The results of numerical experiments show that RIL provides a better reflection of model predictive error than AIC. Thus, RIL can be a useful tool in model selection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akaike H (1998) Information theory and an extension of the maximum likelihood principle. In: Selected papers of Hirotugu Akaike. Springer, New York, NY, pp 199ā213
Altinisik Y, Van Lissa CJ, Hoijtink H, Oldehinkel AJ, Kuiper RM (2021) Evaluation of inequality constrained hypotheses using a generalization of the AIC. Psychol Methods 26(5):599. Chicago
Bai Z, Choi KP, Fujikoshi Y (2018) Consistency of AIC and BIC in estimating the number of significant components in high-dimensional principal component analysis. Ann Stat 46(3):1050ā1076
Barron AR (2020) Predicted squared error: a criterion for automatic model selection. In: Self-organizing methods in modeling. CRC Press, pp 87ā103
Bozdogan H (1987) Model selection and Akaikeās information criterion (AIC): the general theory and its analytical extensions. Psychometrika 52(3):345ā370
Burnham KP, Anderson DR, Huyvaert KP (2011) AIC model selection and multimodel inference in behavioral ecology: some background, observations, and comparisons. Behavioral Ecol Sociobiol 65(1):23ā35
Chen J, Chen Z (2012) Extended BIC for small-n-large-p sparse GLM. Stat Sin 22(2):555ā574. http://www.jstor.org/stable/24310025
Ding J, Tarokh V, Yang Y (2018) Model selection techniques: an overview. IEEE Sign Process Mag 35(6):16ā34
Dormann CF, Calabrese JM, Guillera-Arroita G, Matechou E, Bahn V, BartoÅ K, Hartig F (2018) Model averaging in ecology: a review of Bayesian, information-theoretic, and tactical approaches for predictive inference. Ecol Monogr 88(4):485ā504
Dziak JJ, Coffman DL, Lanza ST, Li R, Jermiin LS (2020) Sensitivity and specificity of information criteria. Briefings Bioinform 21(2):553ā565
Heinze G, Wallisch C, Dunkler D (2018) Variable selection-a review and recommendations for the practicing statistician. Biometrical J 60(3):431ā449
Kalyaanamoorthy S, Minh BQ, Wong TK, Von Haeseler A, Jermiin LS (2017) ModelFinder: fast model selection for accurate phylogenetic estimates. Nat methods 14(6):587ā589
Kamalov F, Thabtah F (2017) A feature selection method based on ranked vector scores of features for classification. Ann Data Sci 4(4):483ā502
Kamalov F (2021) Orthogonal variance decomposition based feature selection. Expert Syst Appl 182:115191
Khan FM, Gupta R (2020) ARIMA and NAR based prediction model for time series analysis of COVID-19 cases in India. J Saf Sci Resilience 1(1):12ā18
Kuiper R (2022) AIC-type theory-based model selection for structural equation models. Struct Eq Model Multidisc J 29(1):151ā158
Lefort V, Longueville JE, Gascuel O (2017) SMS: smart model selection in PhyML. Mol Biol Evol 34(9):2422ā2424
Li H, Yang Z, Yan W (2022) An improved AIC onset-time picking method based on regression convolutional neural network. Mech Syst Sign Process 171:108867
Li Y, Zhang Q, Wang L, Liang L (2021) An AIC-based approach to identify the most influential variables in eco-efficiency evaluation. Expert Syst Appl 167:113883
Liu W, Rioul O, Beaudouin-Lafon M (2023) Bayesian information gain to design interaction
Mahmud N, Fricker Z, Hubbard RA, Ioannou GN, Lewis JD, Taddei TH, Kaplan DE (2021) Risk prediction models for post-operative mortality in patients with cirrhosis. Hepatology 73(1):204ā218
Mulder J, Raftery AE (2022) BIC extensions for order-constrained model selection. Sociol Methods Res 51(2):471ā498
Piironen J, Vehtari A (2017) Comparison of Bayesian predictive methods for model selection. Stat Comput 27(3):711ā735
Pham H (2019) A new criterion for model selection. Mathematics 7(12):1215
Qasim OS, Algamal ZY (2018) Feature selection using particle swarm optimization-based logistic regression model. Chemometr. Intell Lab Syst 182:41ā46
Raschka S (2018) Model evaluation, model selection, and algorithm selection in machine learning. arXiv preprint arXiv:1811.12808
Rajab K, Kamalov F (2021) Finite sample based mutual information. IEEE Access 9:118871ā118879
Schnapp S Sabato S (2021) Active feature selection for the mutual information criterion. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, no 11, pp 9497ā9504
Schwarz G (1978) Estimating the dimension of a model. Ann Stat 461ā464
Shafiq A, Lone SA, Sindhu TN, Al-Mdallal QM, Rasool G (2021) Statistical modeling for bioconvective tangent hyperbolic nanofluid towards stretching surface with zero mass flux condition. Sci Rep 11(1):1ā11
Sharma PN, Shmueli G, Sarstedt M, Danks N, Ray S (2021) Prediction-oriented model selection in partial least squares path modeling. Decis Sci 52(3):567ā607
Solorio-FernĆ”ndez S, Carrasco-Ochoa JA, MartĆnez-Trinidad JF (2020) A review of unsupervised feature selection methods. Artif Intell Rev 53(2):907ā948
Taylor DC, Snipes M, Barber NA (2018) Indicators of hotel profitability: model selection using Akaike information criteria. Tour Hosp Res 18(1):61ā71
Thabtah F, Kamalov F, Hammoud S, Shahamiri SR (2020) Least loss: a simplified filter method for feature selection. Inf Sci 534:1ā15
Tredennick AT, Hooker G, Ellner SP, Adler PB (2021) A practical guide to selecting models for exploration, inference, and prediction in ecology. Ecology 102(6):e03336
Wagenmakers EJ, Farrell S (2004) AIC model selection using Akaike weights. Psychon Bull Rev 11(1):192ā196
Yang W, Zhang D, Peng L, Zhuge C, Hong L (2021) Rational evaluation of various epidemic models based on the COVID-19 data of China. Epidemics 37:100501
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kamalov, F., Moussa, S., Reyes, J.A. (2023). Regularized Information Loss forĀ Improved Model Selection. In: Rajakumar, G., Du, KL., Rocha, Ć. (eds) Intelligent Communication Technologies and Virtual Mobile Networks. ICICV 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 171. Springer, Singapore. https://doi.org/10.1007/978-981-99-1767-9_58
Download citation
DOI: https://doi.org/10.1007/978-981-99-1767-9_58
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1766-2
Online ISBN: 978-981-99-1767-9
eBook Packages: EngineeringEngineering (R0)