Any Pearson correlation equivalent for time series data?

[E. Bernardo]

Dear All,

Is there a Pearson correlation equivalent for time series data in SPSS Forecasting?

I already posted this issue some few weeks ago, but I need to re-post the same by rephrasing the question so that everybody understands.

Thank you.

Eins

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[Maguin, Eugene]

What are you asking for? Let’s be specific. You have one or more series, call them X, Y, Z, etc. So you either compute auto correlation as lag k or cross correlations at lag k. I looked at the algorithm book and the sample auto correlation, computationally, is a pearson correlation. The variance formula is different however.

Gene Maguin

 

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of E. Bernardo
Sent: Tuesday, July 15, 2014 12:36 AM
To: [hidden email]
Subject: Any Pearson correlation equivalent for time series data?

 

Dear All,

 

Is there a Pearson correlation equivalent for time series data in SPSS Forecasting?

I already posted this issue some few weeks ago, but I need to re-post the same by rephrasing the question so that everybody understands.

 

Thank you.

Eins

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

[E. Bernardo]

Gene and ALL,

Thank you for your helpful comments. The cross-correlation at lag k is the one that I have been looking for.  However, I have a follow-up question. As cited in the SPSS manual, "the best approach is to create time series model for both series and then cross-correlate the residuals". I dont understand the rationale why we cross-correlate the noise residuals.  Can somebody enlighten why the NOISE RESIDUALS are to be cross-correlated, rather than the original time series data?

Thank you.
E. Bernardo

On Wednesday, July 16, 2014 2:08 AM, "Maguin, Eugene" <[hidden email]> wrote:

What are you asking for? Let’s be specific. You have one or more series, call them X, Y, Z, etc. So you either compute auto correlation as lag k or cross correlations at lag k. I looked at the algorithm book and the sample auto correlation, computationally, is a pearson correlation. The variance formula is different however.

Gene Maguin

 

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of E. Bernardo
Sent: Tuesday, July 15, 2014 12:36 AM
To: [hidden email]
Subject: Any Pearson correlation equivalent for time series data?

 

Dear All,

 

Is there a Pearson correlation equivalent for time series data in SPSS Forecasting?

I already posted this issue some few weeks ago, but I need to re-post the same by rephrasing the question so that everybody understands.

 

Thank you.

Eins

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD