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›Chow Test for Structural Break
Regression model

Chow Test for Structural Break

Chow Test for Structural Break / Parameter Stability · Also known as: Chow breakpoint test, structural break test, Chow yapısal kırılma testi

The Chow test, introduced by Gregory Chow in 1960, checks whether the coefficients of a linear regression are the same across two subsamples — that is, whether a structural break occurs at a known point such as a policy change, crisis, or regime shift. It compares the fit of a single pooled regression with the combined fit of two separate regressions; a large improvement from splitting indicates the relationship differs between the two periods or groups.

ScholarGate
  1. Regression model
  2. v1
  3. 1 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.

Chow Test
Multiple Linear Regressi…OLS RegressionBai-Perron TestCUSUM TestQuandt-Andrews TestStructural Break ARIMA M…

When to use it

Use the Chow test when you have a specific, known candidate breakpoint — a date of policy reform, a recession, a structural reform, or a natural grouping — and want to test whether the regression relationship is stable across it. It requires enough observations on both sides of the break to estimate the full model twice and assumes equal error variance across the two regimes. When the breakpoint is unknown, a single Chow test is inappropriate (testing every possible date inflates the error rate); use sup-Wald / Quandt-Andrews or Bai-Perron tests designed to search for breaks. When variances differ across regimes, prefer a robust Wald version. The forecast (predictive) form of the test handles the case where one subsample is too small to estimate separately.

Strengths & limitations

Strengths
  • Provides a direct, interpretable F-test for whether a regression relationship shifts at a known point.
  • Simple to compute from three residual sums of squares.
  • Flexible: can test a break in all coefficients or, with interaction terms, in a subset.
  • A long-established, widely taught tool for parameter-stability analysis.
Limitations
  • Requires the breakpoint to be known and pre-specified; it cannot search for an unknown break.
  • Assumes equal error variance across subsamples — heteroskedasticity across regimes distorts it.
  • Needs sufficient observations in each subsample to estimate the full model twice.
  • Tests a single break; multiple or gradual breaks require other procedures.

Frequently asked

What is a structural break?

A structural break is a change in the parameters of the model — the intercept and/or slopes — at some point in the sample, so that the relationship between the variables differs before and after. The Chow test checks for such a change at a known breakpoint.

What if I don't know where the break is?

The standard Chow test requires a known breakpoint. If the date is unknown, do not simply test every candidate and pick the largest statistic — that inflates the false-positive rate. Use tests designed for unknown breaks, such as the Quandt-Andrews sup-Wald test or the Bai-Perron procedure for multiple breaks.

Does the Chow test assume equal variances?

Yes. The classic F-form assumes the error variance is the same in both subsamples. If the variances differ across regimes, the test can be misleading; a Wald test using heteroskedasticity-robust standard errors is the appropriate alternative.

Sources

  1. Chow, G. C. (1960). Tests of equality between sets of coefficients in two linear regressions. Econometrica, 28(3), 591–605. DOI: 10.2307/1910133 ↗

How to cite this page

ScholarGate. (2026, June 2). Chow Test for Structural Break / Parameter Stability. ScholarGate. https://scholargate.app/en/econometrics/chow-test

Related methods

Multiple Linear RegressionOLS Regression

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.

  • Multiple Linear RegressionStatistics↔ compare
  • OLS RegressionEconometrics↔ compare
Compare side by side →

Referenced by

Bai-Perron TestCUSUM TestQuandt-Andrews TestStructural Break ARIMA Model

Similar methods

Quandt-Andrews TestStructural Break OLSStructural Break Hausman TestBai-Perron TestCUSUM TestStructural Break Fixed Effects ModelStructural Break Panel Data AnalysisStructural Break ADF Unit Root Test

Related reference concepts

EconometricsMultivariate Analysis of VarianceMultivariate Multiple RegressionMultivariate RegressionStructural Equation ModelingCross-Validation

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

ScholarGate — Chow Test (Chow Test for Structural Break / Parameter Stability). Retrieved 2026-07-21 from https://scholargate.app/en/econometrics/chow-test · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Gregory C. Chow
Year
1960
Type
Test for structural break in regression coefficients
NullHypothesis
Coefficients are equal across subsamples (no break)
Distribution
F
MinSample
40
Related methods
Multiple Linear RegressionOLS Regression
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