Cointegração (Engle-Granger)

Cointegration (Engle-Granger) is a statistical technique used to verify the existence of relationships between time series. It seeks to determine whether two or more series are cointegrated, i.e., if they share a common trend.

Cointegration is crucial in economic and financial analyses, as it allows identifying patterns and relationships between variables that may not be apparent at first glance. With this technique, it is possible to determine if a series is stationary relative to another.

The Engle-Granger formula, which is the basis for cointegration, involves performing a regression between the series and checking the stationarity of the residuals. If the residuals are stationary, it is possible to conclude that the series are cointegrated.

Cointegration is also useful for forecasting and modeling time series. By identifying cointegrating relationships, it is possible to improve the accuracy of forecasts and better understand the behavior of the series.