Simultaneous equations model (SEM)

A simultaneous equations model (SEM) is a type of statistical model in econometrics that consists of multiple interrelated equations representing the relationships between different variables simultaneously.
Updated: Jun 7, 2024

3 key takeaways

Copy link to section
  • SEMs account for the mutual dependence between variables, providing a more comprehensive understanding of complex economic systems.
  • Identifying and estimating SEMs require specialized techniques, such as instrumental variables and two-stage least squares.
  • SEMs are widely used in economics to analyze systems where variables influence each other reciprocally, such as supply and demand.

What is a simultaneous equations model?

Copy link to section

A simultaneous equations model (SEM) consists of multiple equations that represent the relationships between variables that influence each other simultaneously. Unlike single-equation models, where one variable is assumed to depend on others without reciprocal influence, SEMs recognize that changes in one variable can affect others, which in turn can impact the initial variable.

For example, in the context of supply and demand in a market, the price of a good and the quantity supplied and demanded are determined simultaneously. The quantity demanded depends on the price, and the price is influenced by both the quantity supplied and demanded.

Structure of SEMs

Copy link to section

SEMs typically involve endogenous and exogenous variables:

  • Endogenous variables: Variables that are determined within the system of equations. In a market model, these would include price and quantity.
  • Exogenous variables: Variables that influence the endogenous variables but are not affected by them within the model. Examples might include income, tastes, or technology.

A basic SEM for supply and demand might look like this:

Demand equation: Q_d = alpha_0 + alpha_1 P + alpha_2 Y + u_1

Supply equation: Q_s = beta_0 + beta_1 P + beta_2 C + u_2


  • Q_d is the quantity demanded.
  • Q_s is the quantity supplied.
  • P is the price.
  • Y is an exogenous variable representing income.
  • C is an exogenous variable representing production costs.
  • u_1 and u_2 are error terms.

Applications of SEMs

Copy link to section

SEMs are widely used in economics and other social sciences to analyze complex systems where variables interact with each other. Common applications include:

  • Macroeconomic models: Analyzing relationships between GDP, inflation, interest rates, and other macroeconomic variables.
  • Market models: Studying supply and demand dynamics, price formation, and market equilibrium.
  • Labor economics: Examining the interplay between wages, employment, and labor supply and demand.

Identifying and estimating SEMs

Copy link to section

Identifying and estimating SEMs involves specialized econometric techniques because the simultaneous nature of the relationships creates complications for standard estimation methods like ordinary least squares (OLS).

  • Identification: Before estimating an SEM, it must be determined whether the model is identified, meaning there is enough information to uniquely estimate the parameters. Identification often requires the use of exclusion restrictions, where certain exogenous variables are assumed to affect only specific endogenous variables.
  • Estimation methods: Common methods for estimating SEMs include instrumental variables (IV) and two-stage least squares (2SLS). These methods help address the issue of endogeneity, where explanatory variables are correlated with the error terms.

Benefits and challenges of SEMs

Copy link to section

SEMs offer several advantages in econometric analysis:

  • Realistic modeling: By accounting for mutual dependencies between variables, SEMs provide a more realistic representation of economic systems.
  • Comprehensive analysis: SEMs allow for the simultaneous analysis of multiple relationships, leading to a deeper understanding of complex interactions.
  • Policy insights: SEMs can be used to simulate the effects of policy changes on different parts of the economy, offering valuable insights for policymakers.

Despite their advantages, SEMs also present several challenges:

  • Complexity: Developing and estimating SEMs can be complex, requiring advanced econometric techniques and substantial computational resources.
  • Data requirements: SEMs often require large amounts of data to ensure accurate estimation and identification.
  • Assumptions: The validity of SEM results depends on the correctness of the underlying assumptions, such as the exogeneity of certain variables and the specification of the model.

Understanding simultaneous equations models is essential for analyzing systems with interdependent variables and making informed decisions based on comprehensive economic analysis. For further exploration, one might study specific techniques for identifying and estimating SEMs, applications in different fields of economics, and the development of software tools for SEM analysis.

Sources & references
Risk disclaimer
AI Financial Assistant
Arti is a specialized AI Financial Assistant at Invezz, created to support the editorial team. He leverages both AI and the knowledge base, understands over 100,000... read more.