IDEAS home Printed from https://ideas.repec.org/a/spr/compst/v40y2025i5d10.1007_s00180-024-01559-1.html
   My bibliography  Save this article

A new class of information criteria for improved prediction in the presence of training/validation data heterogeneity

Author

Listed:
  • Javier E. Flores

    (Pacific Northwest National Laboratory)

  • Joseph E. Cavanaugh

    (University of Iowa)

  • Andrew A. Neath

    (Southern Illinois University Edwardsville)

Abstract

Information criteria provide a cogent approach for identifying models that provide an optimal balance between the competing objectives of goodness-of-fit and parsimony. Models that better conform to a dataset are often more complex, yet such models are plagued by greater variability in estimation and prediction. Conversely, overly simplistic models reduce variability at the cost of increases in bias. Asymptotically efficient criteria are those that, for large samples, select the fitted candidate model whose predictors minimize the mean squared prediction error, optimizing between prediction bias and variability. In the context of prediction, asymptotically efficient criteria are thus a preferred tool for model selection, with the Akaike information criterion (AIC) being among the most widely used. However, asymptotic efficiency relies upon the assumption of a panel of validation data generated independently from, but identically to, the set of training data. We argue that assuming identically distributed training and validation data is misaligned with the premise of prediction and often violated in practice. This is most apparent in a regression context, where assuming training/validation data homogeneity requires identical panels of regressors. We therefore develop a new class of predictive information criteria (PIC) that do not assume training/validation data homogeneity and are shown to generalize AIC to the more practically relevant setting of training/validation data heterogeneity. The analytic properties and predictive performance of these new criteria are explored within the traditional regression framework. We consider both simulated and real-data settings. Software for implementing these methods is provided in the R package, picR, available through CRAN.

Suggested Citation

  • Javier E. Flores & Joseph E. Cavanaugh & Andrew A. Neath, 2025. "A new class of information criteria for improved prediction in the presence of training/validation data heterogeneity," Computational Statistics, Springer, vol. 40(5), pages 2389-2423, June.
  • Handle: RePEc:spr:compst:v:40:y:2025:i:5:d:10.1007_s00180-024-01559-1
    DOI: 10.1007/s00180-024-01559-1
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s00180-024-01559-1
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1007/s00180-024-01559-1?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Jiming Jiang & Thuan Nguyen & J. Sunil Rao, 2015. "The E-MS Algorithm: Model Selection With Incomplete Data," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 110(511), pages 1136-1147, September.
    2. Claeskens,Gerda & Hjort,Nils Lid, 2008. "Model Selection and Model Averaging," Cambridge Books, Cambridge University Press, number 9780521852258, Enero-Abr.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Zhongqi Liang & Qihua Wang & Yuting Wei, 2022. "Robust model selection with covariables missing at random," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 74(3), pages 539-557, June.
    2. Yuting Wei & Qihua Wang & Wei Liu, 2021. "Model averaging for linear models with responses missing at random," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 73(3), pages 535-553, June.
    3. Wei, Yuting & Wang, Qihua & Duan, Xiaogang & Qin, Jing, 2021. "Bias-corrected Kullback–Leibler distance criterion based model selection with covariables missing at random," Computational Statistics & Data Analysis, Elsevier, vol. 160(C).
    4. Jeffrey S. Racine & Qi Li & Dalei Yu & Li Zheng, 2023. "Optimal Model Averaging of Mixed-Data Kernel-Weighted Spline Regressions," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 41(4), pages 1251-1261, October.
    5. Philippe Goulet Coulombe & Maxime Leroux & Dalibor Stevanovic & Stéphane Surprenant, 2022. "How is machine learning useful for macroeconomic forecasting?," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 37(5), pages 920-964, August.
    6. Davide Fiaschi & Andrea Mario Lavezzi & Angela Parenti, 2020. "Deep and Proximate Determinants of the World Income Distribution," Review of Income and Wealth, International Association for Research in Income and Wealth, vol. 66(3), pages 677-710, September.
    7. Kurisu, Daisuke & Otsu, Taisuke, 2025. "Model averaging for global Fréchet regression," LSE Research Online Documents on Economics 126533, London School of Economics and Political Science, LSE Library.
    8. Bhattacharya, Debopam & Dupas, Pascaline, 2012. "Inferring welfare maximizing treatment assignment under budget constraints," Journal of Econometrics, Elsevier, vol. 167(1), pages 168-196.
    9. Schomaker Michael & Heumann Christian, 2011. "Model Averaging in Factor Analysis: An Analysis of Olympic Decathlon Data," Journal of Quantitative Analysis in Sports, De Gruyter, vol. 7(1), pages 1-15, January.
    10. Tumala, Mohammed M & Olubusoye, Olusanya E & Yaaba, Baba N & Yaya, OlaOluwa S & Akanbi, Olawale B, 2017. "Forecasting Nigerian Inflation using Model Averaging methods: Modelling Frameworks to Central Banks," MPRA Paper 88754, University Library of Munich, Germany, revised Feb 2018.
    11. José Manuel Cordero Ferrera & Manuel Muñiz Pérez & Rosa Simancas Rodríguez, 2015. "The influence of socioeconomic factors on cognitive and non-cognitive educational outcomes," Investigaciones de Economía de la Educación volume 10, in: Marta Rahona López & Jennifer Graves (ed.), Investigaciones de Economía de la Educación 10, edition 1, volume 10, chapter 21, pages 413-438, Asociación de Economía de la Educación.
    12. Naoya Sueishi & Arihiro Yoshimura, 2017. "Focused Information Criterion for Series Estimation in Partially Linear Models," The Japanese Economic Review, Japanese Economic Association, vol. 68(3), pages 352-363, September.
    13. Liao, Jun & Zou, Guohua, 2020. "Corrected Mallows criterion for model averaging," Computational Statistics & Data Analysis, Elsevier, vol. 144(C).
    14. Miao Han & Liuquan Sun & Yutao Liu & Jun Zhu, 2018. "Joint analysis of recurrent event data with additive–multiplicative hazards model for the terminal event time," Metrika: International Journal for Theoretical and Applied Statistics, Springer, vol. 81(5), pages 523-547, July.
    15. Gildas Mazo & François Portier, 2021. "Parametric versus nonparametric: The fitness coefficient," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 48(4), pages 1344-1383, December.
    16. Anwen Yin, 2024. "Predictive model averaging with parameter instability and heteroskedasticity," Bulletin of Economic Research, Wiley Blackwell, vol. 76(2), pages 418-442, April.
    17. Gerda Claeskens & Fabrizio Consentino, 2008. "Variable Selection with Incomplete Covariate Data," Biometrics, The International Biometric Society, vol. 64(4), pages 1062-1069, December.
    18. Cornelius Fritz & Michael Lebacher & Göran Kauermann, 2020. "Tempus volat, hora fugit: A survey of tie‐oriented dynamic network models in discrete and continuous time," Statistica Neerlandica, Netherlands Society for Statistics and Operations Research, vol. 74(3), pages 275-299, August.
    19. María José Lombardía & Esther López‐Vizcaíno & Cristina Rueda, 2017. "Mixed generalized Akaike information criterion for small area models," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 180(4), pages 1229-1252, October.
    20. Edvard Bakhitov, 2020. "Frequentist Shrinkage under Inequality Constraints," Papers 2001.10586, arXiv.org.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:compst:v:40:y:2025:i:5:d:10.1007_s00180-024-01559-1. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.