Auto-Correlation, Partial Auto-Correlation, Cross Correlation and Partial Cross Correlation Function

This allows evaluation of ACC, PACC, CCF, PCCF as the function of lags.

Time series analysis can be defined as prediction of future values of a random process given previous values. An important part of modelling is the decision of how many of the antecedent values should be used to predict the future. Auto-correlation function demonstrates the correlation coefficient between two series, original series and the lagged series. AC coefficients often die slowly. PACF determines the Correlation coefficient between original and lagged series given that the intermediate values are known. A note: These two should serve as the first step towards modelling. Please see readme for additional information and warranty.
For two processes, Cross-Crorrelation and Partial Cross correlations are added as well.