{
  "title": "Parameter Proliferation in Nowcasting: Issues and Approaches—An Application to Nowcasting China’s Real GDP",
  "publication": "IMF Working Papers, October 24, 2025",
  "sourceUrl": "https://www.imf.org/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013",
  "canonical": "https://www.imf.org/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013",
  "overlayPath": "/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/index.md",
  "summary": "This paper evaluates three approaches to address parameter proliferation issue in nowcasting: (i) variable selection using adjusted stepwise autoregressive integrated moving average with exogenous variables (AS-ARIMAX); (ii) regularization in machine learning (ML); and (iii) dimensionality reduction",
  "sections": [
    {
      "heading": "Research objective and scope",
      "content": "- Evaluate three approaches to address parameter proliferation in nowcasting:\n  - Variable selection using adjusted stepwise autoregressive integrated moving average with exogenous variables (AS-ARIMAX).\n  - Regularization in machine learning (ML).\n  - Dimensionality reduction via principal component analysis (PCA).\n- Empirical application: nowcasting China's annualized real GDP growth rate.\n- Data and estimation window:\n  - Utilizes 166 variables.\n  - Models estimated from 2007Q2 to 2019Q4 using rolling-window regression.\n  - Pseudo out-of-sample comparison for 2020Q1 to 2023Q1."
    },
    {
      "heading": "Methodology and models compared",
      "content": "- Variable-selection approach: AS-ARIMAX implemented within Bridge-type models.\n- Regularization approaches: Ridge Regression, LASSO, and Elastic Net.\n- Dimensionality reduction approach: principal component analysis (PCA) feeding into dynamic factor models (DFM).\n- Nowcasting model families evaluated:\n  - Bridge\n  - MIDAS\n  - U-MIDAS\n  - Dynamic factor model (DFM)\n  - Machine learning techniques (Ridge Regression, LASSO, Elastic Net)\n- Evaluation framework:\n  - Rolling-window regression estimation over 2007Q2–2019Q4.\n  - Pseudo out-of-sample performance comparison over 2020Q1–2023Q1."
    },
    {
      "heading": "Key findings",
      "content": "- LASSO results:\n  - The LASSO method outperforms all other models, but only when guided by economic judgment and sign restrictions in variable selection.\n- Simpler models:\n  - Bridge models combined with AS-ARIMAX variable selection yield reliable estimates nearly comparable to those from LASSO.\n  - Effective variable selection is crucial for capturing strong signals, enabling simpler methods to perform well.\n- Implication on approaches:\n  - Regularization (LASSO) can dominate when combined with domain knowledge and sign constraints.\n  - Dimensionality reduction via PCA and other techniques may be less effective than targeted variable selection in this application."
    },
    {
      "heading": "Practical takeaways and recommended practices",
      "content": "- Prioritize effective variable selection to capture strong predictive signals; AS-ARIMAX is a viable approach for Bridge-type models.\n- When using ML regularization methods (e.g., LASSO), incorporate economic judgment and sign restrictions to improve performance.\n- Simpler models with disciplined variable selection can achieve near-state-of-the-art nowcasting accuracy without full-scale ML pipelines.\n\nSource: IMF Working Paper \"Parameter Proliferation in Nowcasting: Issues and Approaches—An Application to Nowcasting China’s Real GDP\" by Paul Cashin, Fei Han, Ivy Sabuga, Jing Xie, and Fan Zhang (October 24, 2025).\n\n---\n\n Content in this bundle\n\n- Working Paper\n  - Working Paper (Markdown version){rel=\"alternate\" type=\"text/markdown\"}\n  - Working Paper (PDF){rel=\"external\" type=\"application/pdf\"}\n\n---\n\nSource: https://www.imf.org/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013"
    }
  ],
  "bullets": [
    "[Markdown version](/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/index.md)",
    "[Structured JSON version](/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/index.json)",
    "[Bundle manifest](/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/bundle-manifest.json)",
    "Authors: Paul Cashin, Fei Han, Ivy Sabuga, Jing Xie, Fan Zhang",
    "Published: October 24, 2025",
    "Series: IMF Working Papers",
    "DOI: https://doi.org/10.5089/9798229027212.001",
    "Evaluate three approaches to address parameter proliferation in nowcasting:",
    "Empirical application: nowcasting China's annualized real GDP growth rate.",
    "Data and estimation window:",
    "Variable-selection approach: AS-ARIMAX implemented within Bridge-type models.",
    "Regularization approaches: Ridge Regression, LASSO, and Elastic Net.",
    "Dimensionality reduction approach: principal component analysis (PCA) feeding into dynamic factor models (DFM).",
    "Nowcasting model families evaluated:",
    "Evaluation framework:",
    "LASSO results:",
    "Simpler models:",
    "Implication on approaches:",
    "Prioritize effective variable selection to capture strong predictive signals; AS-ARIMAX is a viable approach for Bridge-type models.",
    "When using ML regularization methods (e.g., LASSO), incorporate economic judgment and sign restrictions to improve performance.",
    "Simpler models with disciplined variable selection can achieve near-state-of-the-art nowcasting accuracy without full-scale ML pipelines.",
    "**Working Paper**"
  ],
  "related": [
    {
      "title": "Working Paper",
      "role": "paper",
      "sourceUrl": "https://www.imf.org/-/media/files/publications/wp/2025/english/wpiea2025217-source-pdf.pdf",
      "summary": {
        "path": "/-/media/files/publications/wp/2025/english/wpiea2025217-source-pdf.pdf.md",
        "mime": "text/markdown"
      },
      "binary": {
        "path": "/-/media/files/publications/wp/2025/english/wpiea2025217-source-pdf.pdf",
        "mime": "application/pdf"
      }
    }
  ],
  "alternates": {
    "markdown": "/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/index.md",
    "json": "/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/index.json",
    "bundleManifest": "/en/publications/wp/issues/2025/10/24/parameter-proliferation-in-nowcasting-issues-and-approaches-an-application-to-nowcasting-571013/bundle-manifest.json"
  },
  "generatedAtUtc": "2026-09-17T02:29:43.713Z"
}