Why it matters
Submitted through the ingestion workflow. Review and refine the category and supporting notes before treating it as a settled entry.
Notes
SVAR (Structural Vector Autoregression): SVAR is an econometric tool that separates tangled economic data into the underlying independent surprises, or shocks, that drove it, so you can simulate what happens if one of those shocks hits again. When two economic variables move together, you usually cannot tell from the data alone whether A caused B or B caused A. Interest rates and unemployment may move in the same direction, but both causal stories can fit the same numbers. That is the identification problem. A standard VAR predicts today's values from past values across multiple variables at once. It is good at describing the dance between variables, but it does not tell you why the dance is happening. It tells you what tends to happen next, not who is leading. The structural part adds the discipline needed to decompose comovements into clean, independent causes called structural shocks. These are the original surprises in the economy: an oil price spike, a surprise Fed move, a productivity boom. Once the shock hits, GDP, unemployment, inflation, and other variables adjust as the economy digests it. To move from a VAR to an SVAR, you need identifying restrictions. These are extra assumptions that let you unmix the signal into its pure components. They are not fully testable, which is why two economists can look at the same data and disagree about what counts as a pure monetary shock. SVARs are not magic; they are a disciplined way of making assumptions explicit. A good analogy is a cocktail. A VAR tells you what the drink tastes like: sweet, citrusy, bitter. An SVAR tries to reverse-engineer the recipe, such as 30ml gin and 15ml lime. To do that, you have to assume the bartender only used a limited set of ingredients. Another analogy is a sound engineer. The raw recording with drums, guitar, and vocals mixed together is the VAR. Separating it back into individual tracks is what an SVAR does, but only if you are willing to make assumptions about how the tracks were mixed in the first place. Once you have clean shocks, you can run impulse response functions, which show how the economy reacts over time to one pure shock while holding the others fixed. That is why central banks, the IMF, and finance teams use SVARs to answer questions like what happens if the Fed surprises markets with a rate hike. In short, an SVAR is a statistical tool that separates tangled economic data into the independent shocks that drove it, allowing causal what-if simulations.