A New Correlation Coefficient for Bivariate Time-Series Data

Correlation in time series has recently recieved a lot of attentions. Its usage has been getting an important role in Social Science and Finance. For example, pair trading in Finance is interested with the correlation between stock prices, returns etc. In general, Pearsonís correlation coefficient is seen in the area, although it has many assumptions which restrict its usage. In here, we introduce a new correlation coe¢ cient which takes account the lag difference of data points as a moment. It is more convenient to show the the direction of the movements of the two variables over time. We also simulate the main differences between Pearson's and our correlation coe¢ cients in some cases.