LEVEL II
Autocorrelation is the correlation of a time series with a lagged version of itself. It measures the similarity between a given time series and a lagged version of the same time series. Positive autocorrelation means that the time series is positively correlated with a lagged version of itself, while negative autocorrelation means that the time series is negatively correlated with a lagged version of itself.
Positive autocorrelation occurs when a time series is positively correlated with a lagged version of itself, meaning values tend to increase or decrease together over time. Negative autocorrelation occurs when a time series is negatively correlated with a lagged version of itself, meaning values tend to move in opposite directions over time. Positive autocorrelation can cause problems in certain time series analysis methods. It is important to check for autocorrelation in a time series and account for it when selecting and fitting models.
The Durbin-Watson test can be used to check for autocorrelation with a single time lag.
The Breusch-Godfrey test can be used to check for autocorrelation with multiple time lags.
See also: Heteroskedasticity, Multicollinearity
