Cross Correlation
overview     how to     data     see also 

Stat > Time Series > Cross Correlation

Use to compute and plot the cross correlations between two time series, which can be useful in determining if a series of data leads another series and by how many time periods, or lags. Minitab calculates the correlation between the first series and the second series plus or minus the number of lags (K). You can specify the number of lags (K) you want to test. The examples below illustrate how Minitab calculates lags.

K = 0

 

K = –1

 

K = 1

Time 1

Time 2

 

Time 1

Time 2

 

Time 1

Time 2

2

1

 

2

*

 

*

1

4

3

4

1

2

3

6

5

6

3

4

5

 

 

 

 

5

 

6

 

Dialog box items

First series: Enter the column containing the first time series.

Second series: Enter the column containing the second time series.

Default number of lags: Choose to use the default number of lags (K = -(+ 10) to K = +(+ 10), where K is the number of lags and n is the number of observations in the series).

Number of lags: Choose to specify the number of lags desired, then enter the number of lags. For example, if you enter 4, Minitab calculates the cross correlation for + 4 lags.

Store CCF: Check to store the cross correlation functions in the next available column in the worksheet.

Title: Enter a new title to replace the default title on the graphical output.