graph command question

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

graph command question

Maguin, Eugene

I’m using the legacy graph command (v26) to graph some data and also doing a means command to show what I think should be the matching data. But it is not and I’m lost for an explanation.  My graph command is

GRAPH /LINE(multiple)=MEAN(cigs.week.avg nocigs.week.avg amount.week.avg) BY week.

And my means command is

means cigs.week.avg nocigs.week.avg amount.week.avg by week/

   cells=count mean stddev median.

My data have a progressive loss of cases over weeks.

 

To give you some ideas of the differences consider that at week 6 the graph cigs.week.avg shows a value that looks to be about 3.0 but the means table shows a value of 1.20.  The graph show a value of about 2.3 for nocigs.week.avg but the table shows a value 3.31. At the same time the values for week 2 look to be approximately correct.

 

Does anyone have suggestions about how to understand the difference or how to fix the problem? For instance, does how the data are sorted matter?

 

Thanks, Gene Maguin

 

 

===================== 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
Reply | Threaded
Open this post in threaded view
|

Re: graph command question

Jon Peck
By default, GRAPH uses LISTWISE deletion while MEANS uses VARIABLE by VARIABLE deletion/

On Wed, Dec 9, 2020 at 8:32 AM Maguin, Eugene <[hidden email]> wrote:

I’m using the legacy graph command (v26) to graph some data and also doing a means command to show what I think should be the matching data. But it is not and I’m lost for an explanation.  My graph command is

GRAPH /LINE(multiple)=MEAN(cigs.week.avg nocigs.week.avg amount.week.avg) BY week.

And my means command is

means cigs.week.avg nocigs.week.avg amount.week.avg by week/

   cells=count mean stddev median.

My data have a progressive loss of cases over weeks.

 

To give you some ideas of the differences consider that at week 6 the graph cigs.week.avg shows a value that looks to be about 3.0 but the means table shows a value of 1.20.  The graph show a value of about 2.3 for nocigs.week.avg but the table shows a value 3.31. At the same time the values for week 2 look to be approximately correct.

 

Does anyone have suggestions about how to understand the difference or how to fix the problem? For instance, does how the data are sorted matter?

 

Thanks, Gene Maguin

 

 

===================== 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]

===================== 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
Reply | Threaded
Open this post in threaded view
|

Re: graph command question

Maguin, Eugene

Thanks, Jon. I didn’t do what I’ve encouraged others to do!

 

From: Jon Peck <[hidden email]>
Sent: Wednesday, December 09, 2020 10:38 AM
To: Maguin, Eugene <[hidden email]>
Cc: SPSS List <[hidden email]>
Subject: Re: [SPSSX-L] graph command question

 

By default, GRAPH uses LISTWISE deletion while MEANS uses VARIABLE by VARIABLE deletion/

 

On Wed, Dec 9, 2020 at 8:32 AM Maguin, Eugene <[hidden email]> wrote:

I’m using the legacy graph command (v26) to graph some data and also doing a means command to show what I think should be the matching data. But it is not and I’m lost for an explanation.  My graph command is

GRAPH /LINE(multiple)=MEAN(cigs.week.avg nocigs.week.avg amount.week.avg) BY week.

And my means command is

means cigs.week.avg nocigs.week.avg amount.week.avg by week/

   cells=count mean stddev median.

My data have a progressive loss of cases over weeks.

 

To give you some ideas of the differences consider that at week 6 the graph cigs.week.avg shows a value that looks to be about 3.0 but the means table shows a value of 1.20.  The graph show a value of about 2.3 for nocigs.week.avg but the table shows a value 3.31. At the same time the values for week 2 look to be approximately correct.

 

Does anyone have suggestions about how to understand the difference or how to fix the problem? For instance, does how the data are sorted matter?

 

Thanks, Gene Maguin

 

 

===================== 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]

===================== 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
Reply | Threaded
Open this post in threaded view
|

Re: graph command question

Bruce Weaver
Administrator
This post was updated on .
You didn't RTFM?!  :-O

That's no way to get on Santa's "NICE" list, Gene.  ;-)  



Maguin, Eugene wrote
> Thanks, Jon. I didn’t do what I’ve encouraged others to do!
>
> From: Jon Peck <

> jkpeck@

> >
> Sent: Wednesday, December 09, 2020 10:38 AM
> To: Maguin, Eugene <

> emaguin@

> >
> Cc: SPSS List <

> SPSSX-L@.uga

> >
> Subject: Re: [SPSSX-L] graph command question
>
> By default, GRAPH uses LISTWISE deletion while MEANS uses VARIABLE by
> VARIABLE deletion/





-----
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (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
--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.