SPSSX Discussion

Weighted matrix

Classic

List

Threaded

5 messages Options

Salbod

Weighted matrix

Thanks, Jon for the matrix update.

Speaking of matrices; did you run across a procedure to weight a correlation matrix based on a vector of weights that represent the relative importance of each variable?

Thanks,

Stephen Salbod, Pace University, NYC

===================== 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

David Marso-2

Re: Weighted matrix

I am not sure what this means.
Weight for what purpose.
Importance to what?
Please provide an example for what this would be useful.

=====================
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

Jon Peck

Re: Weighted matrix

Nor I. Weighting cases for a correlation matrix, perhaps, but all the pairwise correlations would be the same as in an unweighted correlation matrix if just variables are weighted.

On Wed, Nov 22, 2017 at 12:02 PM, David Marso <[hidden email]> wrote:

I am not sure what this means.
Weight for what purpose.
Importance to what?
Please provide an example for what this would be useful.

=====================
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

Jon K Peck
[hidden email]

Rich Ulrich

Re: Weighted matrix

In reply to this post by Salbod

Factor analysis?

Rich Ulrich

From: SPSSX(r) Discussion <[hidden email]> on behalf of Salbod, Mr. Stephen <[hidden email]>
Sent: Wednesday, November 22, 2017 1:56:30 PM
To: [hidden email]
Subject: Weighted matrix

Thanks, Jon for the matrix update.

Speaking of matrices; did you run across a procedure to weight a correlation matrix based on a vector of weights that represent the relative importance of each variable?

Thanks,

Stephen Salbod, Pace University, NYC

Salbod

Re: Weighted matrix

In reply to this post by Jon Peck

Hi Jon, thanks for the feedback. A colleague asked about the weighted correlation matrices just as I was reading your announcement about the enhancements. It appears that weighted correlation matrices are often used in genetic studies (gene co--expression) but can have nice applications for network analyses.

--Steve

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Jon Peck
Sent: Wednesday, November 22, 2017 5:52 PM
To: [hidden email]
Subject: Re: Weighted matrix

Nor I. Weighting cases for a correlation matrix, perhaps, but all the pairwise correlations would be the same as in an unweighted correlation matrix if just variables are weighted.

On Wed, Nov 22, 2017 at 12:02 PM, David Marso <[hidden email]> wrote:

I am not sure what this means.
Weight for what purpose.
Importance to what?
Please provide an example for what this would be useful.

=====================
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

Jon K Peck
[hidden email]