A technique used to detect cyclic activity within the market.

Also known as 'lagged correlation' or 'serial correlation.' This takes the form of a mathematical representation of the degree of similarity between a given time series and a lagged version of the same series over successive intervals of time. The process used to calculate the correlation between two different time series is applied here to one time series in two different forms. Once computed, this figure ranges from -1, which represents perfect negative correlation, and 1, indicating perfect positive correlation. This is often used to predict the future strength of a security based on its past performance.