Instrumental variables (IVs) are used in statistical analysis to [estimate causal relationships](Instrument-based%20Causality.md) when controlled experiments aren't feasible or in cases of simultaneous causality ($X → Y$ and $Y → X$). An instrumental variable (IV) is a third variable, $Z$, that helps isolate the causal effect of an explanatory variable, $X$, on an [outcome (dependent variable)](Dependent%20Variable.md), $Y$. The goal is to estimate the causal effect of the observed, [independent variable](Independent%20Variable.md) $X$ (the endogenous variable) on a response variable $Y$ while accounting for unmeasured confounding. The IV helps isolate the variation in the observed variable that is independent of the confounding.