EUVIMEDDescubrir EUVIMED
Open access · CC BY-NC-ND 4.0

Prediction Modeling With Many Correlated and Zero‐Inflated Predictors: Assessing the Nonnegative Garrote Approach

Mariella Gregorich, Michael Kammer, Harald Mischak, Georg Heinze iD

Statistics in Medicine · 2025-04 · 44 (8-9)

DOI: 10.1002/sim.70062 ↗

At a glance

Journal article in Statistics in Medicine, published online on 2025-04-25. Written by Mariella Gregorich and 3 co-authors. Institution: Center for Medical Data Science, Institute of Clinical Biometrics, Medical University of Vienna, Vienna, Austria. Major MEDLINE topics: Models, Statistical, Mass Spectrometry. Cited 3 times so far (Crossref); 27 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: Österreichischen Akademie der Wissenschaften.

ResumenSubjectsDatos bibliográficosCiteRelated studies

Abstract (original language)

Building prediction models from mass‐spectrometry data is challenging due to the abundance of correlated features with varying degrees of zero‐inflation, leading to a common interest in reducing the features to a concise predictor set with good predictive performance given the experiments' resource‐intensive nature. In this study, we established and examined regularized regression approaches designed to address zero‐inflated and correlated predictors. In particular, we describe a novel two‐stage regularized regression approach (ridge‐garrote) explicitly modeling zero‐inflated predictors using two component variables, comprising a ridge estimator in the first stage and subsequently applying a nonnegative garrotte estimator in the second stage. We contrasted ridge‐garrote with one‐stage methods (ridge, lasso) and other two‐stage regularized regression approaches (lasso‐ridge, ridge‐lasso) for zero‐inflated predictors. We assessed the predictive performance and predictor selection properties of these methods in a comparative simulation study and a real‐data case study with the aim to predict kidney function using peptidomic features derived from mass‐spectrometry. In the simulation study, the predictive performance of all assessed approaches was comparable, yet the ridge‐garrote approach consistently selected more parsimonious models compared to its competitors in most scenarios. While lasso‐ridge achieved higher predictive accuracy than its competitors, it exhibited high variability in the number of selected predictors. Ridge‐lasso exhibited slightly superior predictive accuracy than ridge‐garrote but at the expense of selecting more noise predictors. Overall, ridge emerged as a favorable option when variable selection is not a primary concern, while ridge‐garrote demonstrated notable practical utility in selecting a parsimonious set of predictors, with only minimal compromise in predictive accuracy.

Subjects

MeSH terms (MEDLINE)

Models, StatisticalMass SpectrometryHumansComputer SimulationRegression Analysis

Author keywords

mass‐spectrometrynonnegative garroteregularized regressionzero‐inflation

Authors and institutions

  • Center for Medical Data Science, Institute of Clinical Biometrics, Medical University of Vienna, Vienna, Austria.
  • Department of Medicine III, Division of Nephrology, Medical University of Vienna, Vienna, Austria.
  • School of Cardiovascular and Metabolic Health, University of Glasgow, Glasgow, UK.
  • Mosaiques Diagnostics GmbH, Hannover, Germany.

ORCID profiles: Georg Heinze

Funding

  • Österreichischen Akademie der Wissenschaften

Cite

APA

Gregorich, M., Kammer, M., Mischak, H., & Heinze, G. (2025). Prediction Modeling With Many Correlated and Zero‐Inflated Predictors: Assessing the Nonnegative Garrote Approach. Statistics in Medicine, 44(8-9). https://doi.org/10.1002/sim.70062

Vancouver

Gregorich M, Kammer M, Mischak H, Heinze G. Prediction Modeling With Many Correlated and Zero‐Inflated Predictors: Assessing the Nonnegative Garrote Approach. Statistics in Medicine. 2025;44(8-9). doi:10.1002/sim.70062

BibTeX
@article{Gregorich2025,
  author = {Gregorich, Mariella and Kammer, Michael and Mischak, Harald and Heinze, Georg},
  title = {Prediction Modeling With Many Correlated and Zero‐Inflated Predictors: Assessing the Nonnegative Garrote Approach},
  journal = {Statistics in Medicine},
  year = {2025},
  volume = {44},
  number = {8-9},
  doi = {10.1002/sim.70062}
}
Start for free →