Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Econometrics›Structural Break VAR Model
Regression modelEconometrics / time series

Structural Break VAR Model

Vector Autoregression Model with Structural Breaks · Also known as: VAR with structural breaks, break-point VAR, regime-switching VAR, SB-VAR

The Structural Break VAR model extends the standard Vector Autoregression (VAR) framework by allowing coefficient matrices and error covariance to shift at one or more unknown break dates. It is designed for multivariate time series where economic relationships change abruptly due to policy shifts, financial crises, or major structural events.

ScholarGate
  1. Regression model
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Structural Break VAR Model
Structural Break ARIMA M…Structural break VECMStructural VARVector AutoregressionVector Error Correction…Zivot-Andrews Structural…Fourier VAR modelStructural Break AR ModelStructural break SVAR mo…Structural Break Toda-Ya…

When to use it

Use a structural break VAR when theory or visual inspection suggests that the dynamic relationships among your variables have shifted at least once during the sample period — for example, around a financial crisis, a major policy change, or a structural reform. It is appropriate when you have a multivariate system with at least 50–60 observations per regime so that each segment can be estimated reliably. Do not use it when the sample is short and suspected breaks would leave fewer than 30 observations in a segment, when breaks occur frequently (consider Markov-switching VAR instead), or when a single reduced-form VAR with dummy intercepts adequately captures the shift.

Strengths & limitations

Strengths
  • Captures genuine regime changes in multivariate dynamics without forcing a single set of coefficients on the full sample.
  • Regime-specific impulse responses and variance decompositions provide more accurate pictures of shock transmission in each period.
  • Formal break-point tests (Bai-Perron) control size and can identify multiple breaks simultaneously.
  • Prevents omitted-break bias that can distort Granger causality and cointegration findings.
  • Remains interpretable: each segment is a standard VAR whose coefficients have direct economic meaning.
Limitations
  • Each regime requires sufficient observations; too many breaks relative to sample size leads to imprecise estimates.
  • Break dates are estimated with uncertainty, and inference conditional on estimated breaks understates true variability.
  • The number of parameters grows quickly with the number of variables, lags, and regimes, increasing overfitting risk.
  • Assumes breaks are abrupt (level-shift); gradual or smooth parameter changes require time-varying parameter VAR instead.

Frequently asked

How do I decide how many breaks to allow?

Use the Bai-Perron sequential sup-F testing procedure, which starts from zero breaks and adds breaks one at a time while controlling the overall significance level. Information criteria such as BIC can serve as a cross-check. In practice, two or three breaks are typical for post-war macroeconomic samples.

What is the minimum number of observations per regime?

A common rule of thumb is at least 15% of the total sample or a minimum of 30 observations per segment — whichever is larger — so that each regime's VAR can be estimated with reasonable precision. In practice, 50 or more observations per segment is preferable for reliable impulse-response inference.

Should I use the structural break VAR or a Markov-switching VAR?

Use the structural break VAR when breaks are believed to be permanent and datable (one-time policy changes, crises). Use Markov-switching VAR when the economy cycles between recurring regimes (e.g., expansion and recession) with no fixed transition dates.

Can I test Granger causality across the full sample if I find breaks?

No. Full-sample Granger causality tests are invalid if coefficients are not stable. You should test Granger causality within each regime separately and compare results across regimes.

Does finding a structural break in the VAR invalidate a prior cointegration analysis?

It may. Standard Johansen and Engle-Granger tests have low power or distorted size in the presence of structural breaks. You should use cointegration tests that allow for breaks (e.g., Gregory-Hansen) or re-run the analysis within each regime.

Sources

  1. Bai, J., & Perron, P. (1998). Estimating and testing linear models with multiple structural changes. Econometrica, 66(1), 47–78. DOI: 10.2307/2998540 ↗
  2. Sims, C. A. (1980). Macroeconomics and reality. Econometrica, 48(1), 1–48. DOI: 10.2307/1912017 ↗

How to cite this page

ScholarGate. (2026, June 3). Vector Autoregression Model with Structural Breaks. ScholarGate. https://scholargate.app/en/econometrics/structural-break-var-model

Related methods

Structural Break ARIMA ModelStructural break VECMStructural VARVector AutoregressionVector Error Correction ModelZivot-Andrews Structural Break Test

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Structural Break ARIMA ModelEconometrics↔ compare
  • Structural break VECMEconometrics↔ compare
  • Structural VAREconometrics↔ compare
  • Vector AutoregressionEconometrics↔ compare
  • Vector Error Correction ModelEconometrics↔ compare
  • Zivot-Andrews Structural Break TestEconometrics↔ compare
Compare side by side →

Referenced by

Fourier VAR modelStructural Break AR ModelStructural break SVAR modelStructural Break Toda-Yamamoto CausalityStructural break VECM

Similar methods

Structural break SVAR modelStructural Break AR ModelStructural break VECMStructural Break Granger CausalityStructural Break ARIMA ModelStructural Break OLSStructural VARNonlinear VAR Model

Related reference concepts

EconometricsMathematical and Quantitative MethodsSingle Equation Models • Single VariablesEconometric ModelingTime-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes • State Space ModelsFinancial Econometrics

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Structural Break VAR Model (Vector Autoregression Model with Structural Breaks). Retrieved 2026-07-21 from https://scholargate.app/en/econometrics/structural-break-var-model · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Bai & Perron (structural breaks); Sims (VAR framework)
Year
1980–1998
Type
Multivariate time series model with regime change
DataType
Multivariate time series (continuous)
Subfamily
Econometrics / time series
Related methods
Structural Break ARIMA ModelStructural break VECMStructural VARVector AutoregressionVector Error Correction ModelZivot-Andrews Structural Break Test
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account