Instrumental variables are a statistical technique used in econometrics to estimate causal relationships when controlled experiments are not feasible. They help address issues of endogeneity, where an independent variable is correlated with the error term, potentially biasing results. An instrumental variable is one that is correlated with the independent variable but not directly with the dependent variable, allowing researchers to isolate the effect of the independent variable. For example, in studying the impact of education on income, researchers might use proximity to colleges as an instrumental variable. This variable influences education levels but does not directly affect income, helping to clarify the true relationship between education and earnings.