SPSSX Discussion

syntax to produce summary statistics

Classic

List

Threaded

16 messages Options

Johnny Amora

syntax to produce summary statistics

Deal all,

I have 28 scale variables with values ranging from 0 to 100%. The entire data set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean scores.

I am pleased and thankful for any help about the syntax to produce such data.

Thank you.
Johnny

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

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

ViAnn Beadle

Re: syntax to produce summary statistics

What do you mean by the number of persons with >30 mean scores? And why do you want it twice?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny Amora
Sent: Friday, September 12, 2008 6:49 PM
To: [hidden email]
Subject: syntax to produce summary statistics

Deal all,

I have 28 scale variables with values ranging from 0 to 100%. The entire data set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean scores.

I am pleased and thankful for any help about the syntax to produce such data.

Thank you.
Johnny

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

=======
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

Johnny Amora

Re: syntax to produce summary statistics

I wrote:

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

Then ViAnn wrote:
What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

Reply: There are 4000 persons, right? The mean scores range from 0 to 100%, right? Now, how many of the 4000 have mean scores of greater than 30 percent (>30%)? Hope this is clear.

Johnny

Johnny T. Amora
Statistician, Center for Learning and Performance Assessment
De La Salle-College of Saint Benilde
Manila, Philippines

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 9:05 AM

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny
Amora
Sent: Friday, September 12, 2008 6:49 PM
To: [hidden email]
Subject: syntax to produce summary statistics

Deal all,

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

I am pleased and thankful for any help about the syntax to produce such data.

Thank you.
Johnny

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and
@rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

=======
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

Get your new Email address!
Grab the Email name you've always wanted before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

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

ViAnn Beadle

Re: syntax to produce summary statistics

What is a mean score for a person? Upon what basis is the mean calculated? What is a case here, a person or something else?

From: Johnny Amora [mailto:[hidden email]]
Sent: Friday, September 12, 2008 7:21 PM
To: ViAnn Beadle; [hidden email]
Subject: Re: syntax to produce summary statistics

I wrote:

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

Then ViAnn wrote:

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

Reply: There are 4000 persons, right? The mean scores range from 0 to 100%, right? Now, how many of the 4000 have mean scores of greater than 30 percent (>30%)? Hope this is clear.

Johnny

Johnny T. Amora

Statistician, Center for Learning and Performance Assessment
De La Salle-College of Saint Benilde
Manila, Philippines

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 9:05 AM

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny
Amora
Sent: Friday, September 12, 2008 6:49 PM
To: [hidden email]
Subject: syntax to produce summary statistics

Deal all,

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

I am pleased and thankful for any help about the syntax to produce such data.

Thank you.
Johnny

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and
@rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

=======
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

_____

New <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/> Email names for you!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

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

John Amora

Re: syntax to produce summary statistics

case = person
For mean scores for each variable = sum of person scores divided by 4000.

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: RE: syntax to produce summary statistics
To: [hidden email]
Cc: [hidden email]
Date: Saturday, 13 September, 2008, 9:24 AM

What is a mean score for a person? Upon what basis is the mean calculated? What is a case here, a person or something else?

From: Johnny Amora [mailto:[hidden email]]
Sent: Friday, September 12, 2008 7:21 PM
To: ViAnn Beadle; [hidden email]
Subject: Re: syntax to produce summary statistics

I wrote:

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

Then ViAnn wrote:

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

Reply: There are 4000 persons, right? The mean scores range from 0 to 100%, right? Now, how many of the 4000 have mean scores of greater than 30 percent (>30%)? Hope this is clear.

Johnny

Johnny T. Amora

Statistician, Center for Learning and Performance Assessment
De La Salle-College of Saint Benilde
Manila, Philippines

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:
From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 9:05 AMWhat do you mean by the number of persons with >30 mean scores? And why doyou want it twice? -----Original Message-----From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of JohnnyAmoraSent: Friday, September 12, 2008 6:49 PMTo: [hidden email]: syntax to produce summary statistics Deal all, I have 28 scale variables with values ranging from 0 to 100%. The entire dataset has n=4000. I want that my output would have the following format:First column: Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.Second Column: should contain the mean scores.Third column: should contain the standard deviation of scoresFourth column: Should contain the number of persons with >30 mean scores.Fifth or last Column: Should contain the mean of those persons with >30 meanscores. I am pleased and thankful for any help
about the syntax to produce such data. Thank you.Johnny New Email addresses available on Yahoo!Get the Email name you've always wanted on the new @ymail [hidden email] before someone else does!http://mail.promotions.yahoo.com/newdomains/ph/ =======To manage your subscription to SPSSX-L, send a message [hidden email] (not to SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD =====================To manage your subscription to SPSSX-L, send a message [hidden email] (not to SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD

New Email names for you!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

Get your preferred Email name!
Now you can @ymail.com and @rocketmail.com.
http://mail.promotions.yahoo.com/newdomains/ph/

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

ViAnn Beadle

Re: syntax to produce summary statistics

So you’re looking for the percentage of people whose score is greater than 30*mean of that variable?

From: Johnny Amora [mailto:[hidden email]]
Sent: Friday, September 12, 2008 7:31 PM
To: ViAnn Beadle; [hidden email]
Subject: RE: syntax to produce summary statistics

case = person

For mean scores for each variable = sum of person scores divided by 4000.

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: RE: syntax to produce summary statistics
To: [hidden email]
Cc: [hidden email]
Date: Saturday, 13 September, 2008, 9:24 AM

What is a mean score for a person? Upon what basis is the mean calculated? What is a case here, a person or something else?

From: Johnny Amora [mailto:[hidden email]]
Sent: Friday, September 12, 2008 7:21 PM
To: ViAnn Beadle; [hidden email]
Subject: Re: syntax to produce summary statistics

I wrote:

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

Then ViAnn wrote:

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

Reply: There are 4000 persons, right? The mean scores range from 0 to 100%, right? Now, how many of the 4000 have mean scores of greater than 30 percent (>30%)? Hope this is clear.

Johnny

Johnny T. Amora

Statistician, Center for Learning and Performance Assessment
De La Salle-College of Saint Benilde
Manila, Philippines

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 9:05 AM

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny
Amora
Sent: Friday, September 12, 2008 6:49 PM
To: [hidden email]
Subject: syntax to produce summary statistics

Deal all,

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across
rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

I am pleased and thankful for any help about the syntax to produce such data.

Thank you.
Johnny

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and
@rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

=======
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

_____

<http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/> New Email names for you!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

_____

<http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/> Get your preferred Email name!
Now you can @ymail.com and @rocketmail.com.

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

Juanito Talili

Re: syntax to produce summary statistics

ViAnn, if I may interrupt, is it still not clear to you that johnny is asking the "number of people" whose mean score is greater than 30? If the number of people is available, you can easily compute the percentage, right?

JT

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 1:33 AM

So you’re looking for the percentage of people whose score is greater than
30*mean of that variable?

From: Johnny Amora [mailto:[hidden email]]
Sent: Friday, September 12, 2008 7:31 PM
To: ViAnn Beadle; [hidden email]
Subject: RE: syntax to produce summary statistics

case = person

For mean scores for each variable = sum of person scores divided by 4000.

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: RE: syntax to produce summary statistics
To: [hidden email]
Cc: [hidden email]
Date: Saturday, 13 September, 2008, 9:24 AM

What is a mean score for a person? Upon what basis is the mean calculated? What
is a case here, a person or something else?

From: Johnny Amora [mailto:[hidden email]]
Sent: Friday, September 12, 2008 7:21 PM
To: ViAnn Beadle; [hidden email]
Subject: Re: syntax to produce summary statistics

I wrote:

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

Then ViAnn wrote:

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

Reply: There are 4000 persons, right? The mean scores range from 0 to 100%,
right? Now, how many of the 4000 have mean scores of greater than 30 percent
(>30%)? Hope this is clear.

Johnny

Johnny T. Amora

Statistician, Center for Learning and Performance Assessment
De La Salle-College of Saint Benilde
Manila, Philippines

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 9:05 AM

What do you mean by the number of persons with >30 mean scores? And why do
you want it twice?

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Johnny
Amora
Sent: Friday, September 12, 2008 6:49 PM
To: [hidden email]
Subject: syntax to produce summary statistics

Deal all,

I have 28 scale variables with values ranging from 0 to 100%. The entire data
set has n=4000. I want that my output would have the following format:
First column: Should contain the 28 variables appeared downward across
rows.
Thus this column contains 29 rows including the heading.
Second Column: should contain the mean scores.
Third column: should contain the standard deviation of scores
Fourth column: Should contain the number of persons with >30 mean scores.
Fifth or last Column: Should contain the mean of those persons with >30 mean
scores.

I am pleased and thankful for any help about the syntax to produce such data.

Thank you.
Johnny

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and
@rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

=======
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

_____

<http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>
New Email names for you!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

_____

<http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>
Get your preferred Email name!
Now you can @ymail.com and @rocketmail.com.

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

Get your preferred Email name!
Now you can @ymail.com and @rocketmail.com.
http://mail.promotions.yahoo.com/newdomains/ph/

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

Juanito Talili

Re: syntax to produce summary statistics

In reply to this post by Johnny Amora

Johnny, ViAnn,

� Johnny wrote:
>I have 28 scale variables with values ranging from 0 to 100%.
>The entire dataset has n=4000.�

For me, this is understandable. It means that he has a data set consisting of 28 variables with 4000 cases. Thus, his dataset is a 28 by 4000 matrix or a 29 by 4000 matrix including the case#.

His data set looks like this:

case# var1 var2 var3 ... var28
1 - - - ... -
2 - - - ... -
3
.
.
.
4000 - - - ... -

>I want that my output would have the following format:
>First column:� Should contain the 28 variables appeared downward across >rows. Thus this column contains 29 rows including the heading.
>Second Column: should contain the mean scores.Third column: should >contain the standard deviation of scoresFourth column:� Should contain >the number of persons with >30 mean scores.Fifth or last Column: Should >contain the mean of those persons with >30 meanscores.
�
For me (assuming that the data are sample), he wanted an output with the following format:

Column1 column2 column3 column4 column5
(mean) (s.d) (# of cases)
var1 50.1 1.23 500 60.4
var2 65.3 3.54 300 70.1
var3 45.6 2.43 400 59.0
. . . . .
. . . . .
. . . . .
var28 80.0 3.23 100 90.0

From the above fake data, and following johnny's discussion, Column2 represents the mean while column3 is the standard deviation, all computed from above data set. For example: for var1, the mean score of the scores determined from the 4000 cases is 50.1 (column2) and the standard deviation is 1.23 (column3); for va2, the mean score of the 4000 cases is 65.3(column2) and the standard deviation is 3.54 (column3).

Column4 represents the number of persons having scores of greater than its mean. For example in var1, there are 500 cases(people) whose scores are greater than 50.1(its mean). Then the scores of these 500 cases (which are greater than 50.1) have mean of 60.4 (column5).

Hope my thoughts help you Johnny to let ViAnn understands you.

Cheers,
Juanito

From: Juanito Talili [mailto:[hidden email]]
Sent: Friday, September 12, 2008 8:10 PM
To: [hidden email]; ViAnn Beadle
Subject: Re: syntax to produce summary statistics
�

ViAnn,� if I may interrupt, is it still not clear to you that� johnny is asking� the "number of people" whose mean score is greater than 30? If the number of people is available,� you can easily compute the percentage, right?

�

JT

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 1:33 AMSo you’re looking for the percentage of people whose score is greater than30*mean of that variable? � � From: Johnny Amora [mailto:[hidden email]] Sent: Friday, September 12, 2008 7:31 PMTo: ViAnn Beadle; [hidden email]: RE: syntax to produce summary statistics � � � case = person � For mean scores for each variable = sum of person scores divided by 4000. � � � � --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote: � From: ViAnn Beadle <[hidden email]>Subject: RE: syntax to produce summary statisticsTo: [hidden email]: [hidden email]: Saturday, 13 September, 2008, 9:24 AM � What is a mean score for a person? Upon what basis is the mean calculated? Whatis a case here, a person or something else? � � From: Johnny Amora [mailto:[hidden email]] Sent: Friday, September 12, 2008 7:21 PMTo: ViAnn Beadle; [hidden email]:
Re: syntax to produce summary statistics � � � I wrote: � � I have 28 scale variables with values ranging from 0 to 100%. The entire dataset has n=4000.� I want that my output would have the following format:First column:� Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.Second Column: should contain the mean scores.Third column: should contain the standard deviation of scoresFourth column:� Should contain the number of persons with >30 mean scores.Fifth or last Column: Should contain the mean of those persons with >30 meanscores. � Then ViAnn wrote: � What do you mean by the number of persons with >30 mean scores? And why doyou want it twice? � � Reply: There are 4000 persons, right? The mean scores range from 0 to 100%,right? Now, how many of the 4000 have mean scores of greater than 30 percent(>30%)?� Hope this is clear. � � Johnny � Johnny T. Amora � Statistician,
Center for Learning and Performance Assessment De La Salle-College of Saint Benilde Manila, Philippines � � � --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote: � From: ViAnn Beadle <[hidden email]>Subject: Re: syntax to produce summary statisticsTo: [hidden email]: Saturday, 13 September, 2008, 9:05 AM � What do you mean by the number of persons with >30 mean scores? And why doyou want it twice?� -----Original Message-----From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of JohnnyAmoraSent: Friday, September 12, 2008 6:49 PMTo: [hidden email]: syntax to produce summary statistics� Deal all,� I have 28 scale variables with values ranging from 0 to 100%. The entire dataset has n=4000.� I want that my output would have the following format:First column:� Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.Second
Column: should contain the mean scores.Third column: should contain the standard deviation of scoresFourth column:� Should contain the number of persons with >30 mean scores.Fifth or last Column: Should contain the mean of those persons with >30 meanscores.� I am pleased and thankful for any help about the syntax to produce such data.� Thank you.Johnny� � � � � � � � � � � New Email addresses available on Yahoo!Get the Email name you've always wanted on the new @ymail [hidden email] before someone else does!http://mail.promotions.yahoo.com/newdomains/ph/� =======To manage your subscription to SPSSX-L, send a message [hidden email] (not to SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD� =====================To manage your subscription to SPSSX-L, send a message [hidden email] (not to
SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD � � � _____� � � <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>New Email names for you! Get the Email name you've always wanted on the new @ymail and @rocketmail.Hurry before someone else does! � � � _____� � � <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>Get your preferred Email name! Now you can @ymail.com and @rocketmail.com. � ====================To manage your subscription to SPSSX-L, send a message [hidden email] (not to SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

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

ViAnn Beadle

Re: syntax to produce summary statistics

So what is the 30 in the original post?

-----Original Message-----
From: Juanito Talili [mailto:[hidden email]]
Sent: Friday, September 12, 2008 11:40 PM
To: [hidden email]; [hidden email]; [hidden email]
Subject: Re: syntax to produce summary statistics

Johnny, ViAnn,

Johnny wrote:
>I have 28 scale variables with values ranging from 0 to 100%.
>The entire dataset has n=4000.

For me, this is understandable. It means that he has a data set consisting of 28 variables with 4000 cases. Thus, his dataset is a 28 by 4000 matrix or a 29 by 4000 matrix including the case#.

His data set looks like this:

case# var1 var2 var3 ... var28
1 - - - ... -
2 - - - ... -
3
.
.
.
4000 - - - ... -

>I want that my output would have the following format:
>First column: Should contain the 28 variables appeared downward across >rows. Thus this column contains 29 rows including the heading.
>Second Column: should contain the mean scores.Third column: should >contain the standard deviation of scoresFourth column: Should contain >the number of persons with >30 mean scores.Fifth or last Column: Should >contain the mean of those persons with >30 meanscores.

For me (assuming that the data are sample), he wanted an output with the following format:

Column1 column2 column3 column4 column5
(mean) (s.d) (# of cases)
var1 50.1 1.23 500 60.4
var2 65.3 3.54 300 70.1
var3 45.6 2.43 400 59.0
. . . . .
. . . . .
. . . . .
var28 80.0 3.23 100 90.0

From the above fake data, and following johnny's discussion, Column2 represents the mean while column3 is the standard deviation, all computed from above data set. For example: for var1, the mean score of the scores determined from the 4000 cases is 50.1 (column2) and the standard deviation is 1.23 (column3); for va2, the mean score of the 4000 cases is 65.3(column2) and the standard deviation is 3.54 (column3).

Column4 represents the number of persons having scores of greater than its mean. For example in var1, there are 500 cases(people) whose scores are greater than 50.1(its mean). Then the scores of these 500 cases (which are greater than 50.1) have mean of 60.4 (column5).

Hope my thoughts help you Johnny to let ViAnn understands you.

Cheers,
Juanito

From: Juanito Talili [mailto:[hidden email]]
Sent: Friday, September 12, 2008 8:10 PM
To: [hidden email]; ViAnn Beadle
Subject: Re: syntax to produce summary statistics

ViAnn, if I may interrupt, is it still not clear to you that johnny is asking the "number of people" whose mean score is greater than 30? If the number of people is available, you can easily compute the percentage, right?

JT

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

From: ViAnn Beadle <[hidden email]>
Subject: Re: syntax to produce summary statistics
To: [hidden email]
Date: Saturday, 13 September, 2008, 1:33 AMSo you’re looking for the percentage of people whose score is greater than30*mean of that variable? From: Johnny Amora [mailto:[hidden email]] Sent: Friday, September 12, 2008 7:31 PMTo: ViAnn Beadle; [hidden email]: RE: syntax to produce summary statistics case = person For mean scores for each variable = sum of person scores divided by 4000. --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote: From: ViAnn Beadle <[hidden email]>Subject: RE: syntax to pproduce summary statisticsTo: [hidden email]: [hidden email]: Saturday, 13 September, 2008, 9:24 AM What is a mean score for a person? Upon what basis is the mean calculated? Whatis a case here, a person or something else? From: Johnny Amora [mailto:[hidden email]] Sent: Friday, September 12, 2008 7:21 PMTo: ViAnn Beadle; [hidden email]:
Re: syntax to produce summary statistics I wrote: I have 28 scale variables with values ranging from 0 to 100%. The entire dataset has n=4000. I want that my output would have the following format:First column: Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.Second Column: should contain the mean scores.Third column: should contain the standard deviation of scoresFourth column: Should contain the number of persons with >30 mean scores.Fifth or last Column: Should contain the mean of those persons with >30 meanscores. Then ViAnn wrote: What do you mean by the number of persons with >30 mean scores? And why doyou want it twice? Reply: There are 4000 persons, right? The mean scores range from 0 to 100%,right? Now, how many of the 4000 have mean scores of greater than 30 percent(>30%)? Hope this is clear. Johnny Johnny T. Amora Statistician,
Center for Learning and Performance Assessment De La Salle-College of Saint Benilde Manila, Philippines --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote: From: ViAnn Beadle <[hidden email]>Subject: Re: syntax to pproduce summary statisticsTo: [hidden email]: Saturday, 13 September, 2008, 9:05 AM What do you mean by the number of persons with >30 mean scores? And why doyou want it twice? -----Original Message-----From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of JohnnyAmoraSent: Friday, September 12, 2008 6:49 PMTo: [hidden email]: syntax to produce summary statistics Deal all, I have 28 scale variables with values ranging from 0 to 100%. The entire dataset has n=4000. I want that my output would have the following format:First column: Should contain the 28 variables appeared downward across rows. Thus this column contains 29 rows including the heading.Second
Column: should contain the mean scores.Third column: should contain the standard deviation of scoresFourth column: Should contain the number of persons with >30 mean scores.Fifth or last Column: Should contain the mean of those persons with >30 meanscores. I am pleased and thankful for any help about the syntax to produce such data. Thank you.Johnny New Email addresses available on Yahoo!Get the Email name you've always wanted on the new @ymail [hidden email] before someone else does!http://mail.promotions.yahoo.com/newdomains/ph/ =======To manage your subscription to SPSSX-L, send a message [hidden email] (not to SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD =====================To manage your subscription to SPSSX-L, send a message [hidden email] (not to
SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD _____ <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>New Email names for you! Get the Email name you've always wanted on the new @ymail and @rocketmail.Hurry before someone else does! _____ <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>Get your preferred Email name! Now you can @ymail.com and @rocketmail.com. ====================To manage your subscription to SPSSX-L, send a message [hidden email] (not to SPSSX-L), with no body text except thecommand. To leave the list, send the commandSIGNOFF SPSSX-LFor a list of commands to manage subscriptions, send the commandINFO REFCARD

New Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

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

Juanito Talili

Re: syntax to produce summary statistics

I cant imagine that there is idiot in this list!

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

> From: ViAnn Beadle <[hidden email]>
> Subject: Re: syntax to produce summary statistics
> To: [hidden email]
> Date: Saturday, 13 September, 2008, 2:59 PM
> So what is the 30 in the original post?
>
> -----Original Message-----
> From: Juanito Talili [mailto:[hidden email]]
> Sent: Friday, September 12, 2008 11:40 PM
> To: [hidden email]; [hidden email];
> [hidden email]
> Subject: Re: syntax to produce summary statistics
>
> Johnny, ViAnn,
>
> Johnny wrote:
> >I have 28 scale variables with values ranging from 0 to
> 100%.
> >The entire dataset has n=4000.
>
> For me, this is understandable. It means that he has a data
> set consisting of 28 variables with 4000 cases. Thus, his
> dataset is a 28 by 4000 matrix or a 29 by 4000 matrix
> including the case#.
>
> His data set looks like this:
>
> case# var1 var2 var3 ... var28
> 1 - - - ... -
> 2 - - - ... -
> 3
> .
> .
> .
> 4000 - - - ... -
>
>
> >I want that my output would have the following format:
> >First column: Should contain the 28 variables appeared
> downward across >rows. Thus this column contains 29 rows
> including the heading.
> >Second Column: should contain the mean scores.Third
> column: should >contain the standard deviation of
> scoresFourth column: Should contain >the number of
> persons with >30 mean scores.Fifth or last Column: Should
> >contain the mean of those persons with >30
> meanscores.
>
> For me (assuming that the data are sample), he wanted an
> output with the following format:
>
> Column1 column2 column3 column4
> column5
> (mean) (s.d) (# of cases)
> var1 50.1 1.23 500
> 60.4
> var2 65.3 3.54 300
> 70.1
> var3 45.6 2.43 400
> 59.0
> . . . .
> .
> . . . .
> .
> . . . .
> .
> var28 80.0 3.23 100
> 90.0
>
>
> From the above fake data, and following johnny's
> discussion, Column2 represents the mean while column3 is the
> standard deviation, all computed from above data set. For
> example: for var1, the mean score of the scores determined
> from the 4000 cases is 50.1 (column2) and the standard
> deviation is 1.23 (column3); for va2, the mean score of the
> 4000 cases is 65.3(column2) and the standard deviation is
> 3.54 (column3).
>
> Column4 represents the number of persons having scores of
> greater than its mean. For example in var1, there are 500
> cases(people) whose scores are greater than 50.1(its mean).
> Then the scores of these 500 cases (which are greater than
> 50.1) have mean of 60.4 (column5).
>
> Hope my thoughts help you Johnny to let ViAnn understands
> you.
>
> Cheers,
> Juanito
>
>
>
>
>
> From: Juanito Talili [mailto:[hidden email]]
> Sent: Friday, September 12, 2008 8:10 PM
> To: [hidden email]; ViAnn Beadle
> Subject: Re: syntax to produce summary statistics
>
>
>
>
>
>
> ViAnn, if I may interrupt, is it still not clear to you
> that johnny is asking the "number of people" whose
> mean score is greater than 30? If the number of people is
> available, you can easily compute the percentage, right?
>
>
>
> JT
>
>
> --- On Sat, 9/13/08, ViAnn Beadle
> <[hidden email]> wrote:
>
> From: ViAnn Beadle <[hidden email]>
> Subject: Re: syntax to produce summary statistics
> To: [hidden email]
> Date: Saturday, 13 September, 2008, 1:33 AMSo you’re
> looking for the percentage of people whose score is greater
> than30*mean of that variable? From: Johnny Amora
> [mailto:[hidden email]] Sent: Friday, September 12,
> 2008 7:31 PMTo: ViAnn Beadle;
> [hidden email]: RE: syntax to produce
> summary statistics case = person For mean scores for
> each variable = sum of person scores divided by 4000.
> --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]>
> wrote: From: ViAnn Beadle
> <[hidden email]>Subject: RE: syntax to produce
> summary statisticsTo: [hidden email]:
> [hidden email]: Saturday, 13 September, 2008,
> 9:24 AM What is a mean score for a person? Upon what basis
> is the mean calculated? Whatis a case here, a person or
> something else? From: Johnny Amora
> [mailto:[hidden email]] Sent: Friday, September 12,
> 2008 7:21 PMTo: ViAnn Beadle;
> [hidden email]:
> Re: syntax to produce summary statistics I wrote:
> I have 28 scale variables with values ranging from 0 to
> 100%. The entire dataset has n=4000. I want that my output
> would have the following format:First column: Should
> contain the 28 variables appeared downward across rows. Thus
> this column contains 29 rows including the heading.Second
> Column: should contain the mean scores.Third column: should
> contain the standard deviation of scoresFourth column:
> Should contain the number of persons with >30 mean
> scores.Fifth or last Column: Should contain the mean of
> those persons with >30 meanscores. Then ViAnn wrote:
> What do you mean by the number of persons with >30 mean
> scores? And why doyou want it twice? Reply: There are
> 4000 persons, right? The mean scores range from 0 to
> 100%,right? Now, how many of the 4000 have mean scores of
> greater than 30 percent(>30%)? Hope this is clear.
> Johnny Johnny T. Amora Statistician,
> Center for Learning and Performance Assessment De La
> Salle-College of Saint Benilde Manila, Philippines ---
> On Sat, 9/13/08, ViAnn Beadle <[hidden email]>
> wrote: From: ViAnn Beadle
> <[hidden email]>Subject: Re: syntax to produce
> summary statisticsTo: [hidden email]:
> Saturday, 13 September, 2008, 9:05 AM What do you mean by
> the number of persons with >30 mean scores? And why doyou
> want it twice? -----Original Message-----From: SPSSX(r)
> Discussion [mailto:[hidden email]] On Behalf Of
> JohnnyAmoraSent: Friday, September 12, 2008 6:49 PMTo:
> [hidden email]: syntax to produce summary
> statistics Deal all, I have 28 scale variables with values
> ranging from 0 to 100%. The entire dataset has n=4000. I
> want that my output would have the following format:First
> column: Should contain the 28 variables appeared downward
> across rows. Thus this column contains 29 rows including the
> heading.Second
> Column: should contain the mean scores.Third column:
> should contain the standard deviation of scoresFourth
> column: Should contain the number of persons with >30
> mean scores.Fifth or last Column: Should contain the mean of
> those persons with >30 meanscores. I am pleased and
> thankful for any help about the syntax to produce such data.
> Thank you.Johnny New Email addresses available
> on Yahoo!Get the Email name you've always wanted on
> the new @ymail [hidden email] before someone else
> does!http://mail.promotions.yahoo.com/newdomains/ph/
> =======To manage your subscription to SPSSX-L, send a
> message [hidden email] (not to SPSSX-L), with
> no body text except thecommand. To leave the list, send the
> commandSIGNOFF SPSSX-LFor a list of commands to manage
> subscriptions, send the commandINFO REFCARD
> =====================To manage your subscription to SPSSX-L,
> send a message [hidden email] (not to
> SPSSX-L), with no body text except thecommand. To leave
> the list, send the commandSIGNOFF SPSSX-LFor a list of
> commands to manage subscriptions, send the commandINFO
> REFCARD _____
> <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>New
> Email names for you! Get the Email name you've always
> wanted on the new @ymail and @rocketmail.Hurry before
> someone else does! _____
> <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>Get
> your preferred Email name! Now you can @ymail.com and
> @rocketmail.com. ====================To manage your
> subscription to SPSSX-L, send a message
> [hidden email] (not to SPSSX-L), with no body
> text except thecommand. To leave the list, send the
> commandSIGNOFF SPSSX-LFor a list of commands to manage
> subscriptions, send the commandINFO REFCARD
>
>
> New Email addresses available on Yahoo!
> Get the Email name you've always wanted on the new
> @ymail and @rocketmail.
> Hurry before someone else does!
> http://mail.promotions.yahoo.com/newdomains/ph/
>
> =====================
> 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

ViAnn Beadle

Re: syntax to produce summary statistics

I am trying to figure out what Jonny wants so I could perhaps provide a solution and I just don’t understand what mean of an person > 30 is.

If you’re calling me an idiot, stuff it.

From: Juanito Talili [mailto:[hidden email]]
Sent: Saturday, September 13, 2008 7:56 PM
To: [hidden email]; ViAnn Beadle
Subject: Re: syntax to produce summary statistics

I cant imagine that there is idiot in this list!

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

_____

New <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/> Email addresses available on Yahoo!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

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

Art Kendall

Re: syntax to produce summary statistics

In reply to this post by Juanito Talili

*That is totally uncalled for and inappropriate.*

ViAnn is kind enough to share her great expertise with this list. She
has been a great help to many people on this list including myself and I
have been using SPSS since 1972. Her effort to be sure she understood
the question before giving a solution was the mark of a true professional.

As is common in any consultative situation the presenting question
(original post) often needs to be clarified before a useful response
can be made.
The OP was not completely clear. You implicitly saw this as you posted
an interpretation of the OP.

When I read the OP, I read between the lines that the last column would
be the mean score for those people whose score exceeded 30. Since this
was a rather unusual request I concluded I did not understand the
question, perhaps the OP meant over age 30 or something. Since a reply
asking for clarification had already been posted, I waited to see the
clarification.

Art Kendall
Social Research Consultants

Juanito Talili wrote:
> I cant imagine that there is idiot in this list!
>
>
> --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:
>
> <ship>
>

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

Art Kendall
Social Research Consultants

Maguin, Eugene

Re: syntax to produce summary statistics

In reply to this post by Johnny Amora

This statement was confusing to me when I read it. And it remains confusing.

>>Fourth column: Should contain the number of persons with >30 mean scores.

The problem, I think, is understanding the meaning and construction in the
context of the layout out of output table. Following his instructions, the
ouput table will look like this:

>>First column: Should contain the 28 variables appeared downward across
rows. Thus this column contains 29 rows including the heading.
>>Second Column: should contain the (item) mean scores.
>>Third column: should contain the (item) standard deviation of scores
>>Fourth column: Should contain the number of persons with >30 mean scores.
>>Fifth or last Column: Should contain the mean of those persons with >30
mean scores.

VarName Mean StdDev NPersons>30 Mn(NPersons>30)
V1 22.34 12.23 ?? ??
...
V28 32.34 16.34 ?? ??

I interpret Johnny's description of the fourth column to be the number of
persons with a mean greater than 30 on a scale consisting of the 28
variables. If so, then this number is a constant for every variable.
Likewise, the fifth column is constant because it is the mean score of the
28 item scale for that subset of persons whose scale mean was greater than
30.

However, maybe this isn't what is meant. Either way, I think a numerical
example computation is needed because verbal description isn't helping and
people are getting frustrated. How about it, Johnny? Give us computational
example for columns 4 and 5. Actually, do something else also. Tell us the
range of possible scores for the 28 items. I've been assuming that the range
is something like 1-5. Maybe it is 1-100.

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

Albert-Jan Roskam

Re: syntax to produce summary statistics

In reply to this post by Art Kendall

Hi,

--- On Sun, 9/14/08, Art Kendall <[hidden email]> wrote:
> *That is totally uncalled for and inappropriate.*

---> I agree, of course. http://en.wikipedia.org/wiki/Netiquette
--->As for the post, here's my piece of idiocracy ;-)

* calculate overall mean + sd.
compute dummy = 1.
aggr out = * mode=addvariables
/ break = dummy
/ m = mean (var1)
/ sd = mean (var1).

* calculate mean score of those who score 30 or higher.
compute x = 0.
if (m ge 30) x = 1.
aggr out = * mode=addvariables
/ break = x
/ m30plus = mean (var1).
if (x = 0) m30plus = $sysmis.

* calculate number of people who score 30+.
aggr out = *
/ break = dummy
/ m1 = mean (var1)
/ sd = mean (var1)
/ n30plus = sum (x)
/ m30plus = mean (m30plus).

* transpose resulting dataset.
flip.

Cheers!!
Albert-Jan

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

ViAnn Beadle

Re: syntax to produce summary statistics

In reply to this post by Johnny Amora

First, your colleague Juanito does you no favors and you should discourage him from speaking for you. Perhaps he’s not your colleague but you both share remarkably similar IP addresses so maybe you can talk to him personally.

Now to my approach:

This solution produces a report.

The summarize command will easily produce a simple report with variables in the rows and statistics in the columns for all your columns except the last column. The best way to get the numbers in that last column is to make a copy of the source variable but to set all values to missing that are less than or equal to 30. Since you have a copy of each variable, you can’t stuff it into the summarize table as just another column.

My solution is to do all of the calculations with aggregate and then use VARSTOCASES to create a matrix in which each row is a variable and then SUMMARIZE to create a report from the data file.

Here’s my syntax starting with a little input program to create some data.

dataset declare rawdata.

input program.

loop #i=1 to 100.

do repeat x=v1 to v3.

compute x=UNIFORM(100).

end repeat.

end case.

end loop.

end file.

end input program.

*make copies of vars copying values greater than 30.

do repeat x=v1 to v3/trimx=trimv1 to trimv3.

if x>30 trimx=x.

end repeat.

execute.

DATASET DECLARE summary.

AGGREGATE

/OUTFILE=summary

/BREAK=

/v1_mean=MEAN(v1)

/v1_sd=SD(v1)

/v1_pgt=PGT(v1 30)

/v1_mean30=MEAN(trimv1)

/v2_mean=MEAN(v2)

/v2_sd=SD(v2)

/v2_pgt=PGT(v2 30)

/v2_mean30=MEAN(trimv2)

/v3_mean=MEAN(v3)

/v3_sd=SD(v3)

/v3_pgt=PGT(v3 30)

/v3_mean30=MEAN(trimv3).

DATASET ACTIVATE summary.

VARSTOCASES

/ID=id

/MAKE Mean FROM v1_mean v2_mean v3_mean

/MAKE Stdev FROM v1_sd v2_sd v3_sd

/MAKE Percent30 FROM v1_pgt v2_pgt v3_pgt

/MAKE mean30 FROM v1_mean30 v2_mean30 v3_mean30

/INDEX=Index1(3)

/KEEP=

/NULL=KEEP.

var labels index1 "Variable".

value labels index1 1 "v1" 2 "v2" 3 "v3".

var labels Percent30 "Percent of value>30"

Mean30 "Mean of value>30"

Stdev "Standard Deviation".

* make a nice table now.

DATASET ACTIVATE summary.

SUMMARIZE

/TABLES=Index1 Mean Stdev Percent30 mean30

/FORMAT=LIST NOCASENUM NOTOTAL

/CELLS NONE.

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

Ornelas, Fermin-2

Re: syntax to produce summary statistics

In reply to this post by Juanito Talili

I do not think it is acceptable to denigrate someone that is trying to help for free. It serves no purpose whatsoever, her tons of responses to e-mails speak for themselves.

ViAnn is one of the most unselfish individuals willing to share what she knows.

Fermin Ornelas, Ph.D.
Management Analyst III, AZ DES
1789 W. Jefferson Street
Phoenix, AZ 85007
Tel: (602) 542-5639
E-mail: [hidden email]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Juanito Talili
Sent: Saturday, September 13, 2008 6:56 PM
To: [hidden email]
Subject: Re: syntax to produce summary statistics

I cant imagine that there is idiot in this list!

--- On Sat, 9/13/08, ViAnn Beadle <[hidden email]> wrote:

> From: ViAnn Beadle <[hidden email]>
> Subject: Re: syntax to produce summary statistics
> To: [hidden email]
> Date: Saturday, 13 September, 2008, 2:59 PM
> So what is the 30 in the original post?
>
> -----Original Message-----
> From: Juanito Talili [mailto:[hidden email]]
> Sent: Friday, September 12, 2008 11:40 PM
> To: [hidden email]; [hidden email];
> [hidden email]
> Subject: Re: syntax to produce summary statistics
>
> Johnny, ViAnn,
>
> Johnny wrote:
> >I have 28 scale variables with values ranging from 0 to
> 100%.
> >The entire dataset has n=4000.
>
> For me, this is understandable. It means that he has a data
> set consisting of 28 variables with 4000 cases. Thus, his
> dataset is a 28 by 4000 matrix or a 29 by 4000 matrix
> including the case#.
>
> His data set looks like this:
>
> case# var1 var2 var3 ... var28
> 1 - - - ... -
> 2 - - - ... -
> 3
> .
> .
> .
> 4000 - - - ... -
>
>
> >I want that my output would have the following format:
> >First column: Should contain the 28 variables appeared
> downward across >rows. Thus this column contains 29 rows
> including the heading.
> >Second Column: should contain the mean scores.Third
> column: should >contain the standard deviation of
> scoresFourth column: Should contain >the number of
> persons with >30 mean scores.Fifth or last Column: Should
> >contain the mean of those persons with >30
> meanscores.
>
> For me (assuming that the data are sample), he wanted an
> output with the following format:
>
> Column1 column2 column3 column4
> column5
> (mean) (s.d) (# of cases)
> var1 50.1 1.23 500
> 60.4
> var2 65.3 3.54 300
> 70.1
> var3 45.6 2.43 400
> 59.0
> . . . .
> .
> . . . .
> .
> . . . .
> .
> var28 80.0 3.23 100
> 90.0
>
>
> From the above fake data, and following johnny's
> discussion, Column2 represents the mean while column3 is the
> standard deviation, all computed from above data set. For
> example: for var1, the mean score of the scores determined
> from the 4000 cases is 50.1 (column2) and the standard
> deviation is 1.23 (column3); for va2, the mean score of the
> 4000 cases is 65.3(column2) and the standard deviation is
> 3.54 (column3).
>
> Column4 represents the number of persons having scores of
> greater than its mean. For example in var1, there are 500
> cases(people) whose scores are greater than 50.1(its mean).
> Then the scores of these 500 cases (which are greater than
> 50.1) have mean of 60.4 (column5).
>
> Hope my thoughts help you Johnny to let ViAnn understands
> you.
>
> Cheers,
> Juanito
>
>
>
>
>
> From: Juanito Talili [mailto:[hidden email]]
> Sent: Friday, September 12, 2008 8:10 PM
> To: [hidden email]; ViAnn Beadle
> Subject: Re: syntax to produce summary statistics
>
>
>
>
>
>
> ViAnn, if I may interrupt, is it still not clear to you
> that johnny is asking the "number of people" whose
> mean score is greater than 30? If the number of people is
> available, you can easily compute the percentage, right?
>
>
>
> JT
>
>
> --- On Sat, 9/13/08, ViAnn Beadle
> <[hidden email]> wrote:
>
> From: ViAnn Beadle <[hidden email]>
> Subject: Re: syntax to produce summary statistics
> To: [hidden email]
> Date: Saturday, 13 September, 2008, 1:33 AMSo you're
> looking for the percentage of people whose score is greater
> than30*mean of that variable? From: Johnny Amora
> [mailto:[hidden email]] Sent: Friday, September 12,
> 2008 7:31 PMTo: ViAnn Beadle;
> [hidden email]: RE: syntax to produce
> summary statistics case = person For mean scores for
> each variable = sum of person scores divided by 4000.
> --- On Sat, 9/13/08, ViAnn Beadle <[hidden email]>
> wrote: From: ViAnn Beadle
> <[hidden email]>Subject: RE: syntax to produce
> summary statisticsTo: [hidden email]:
> [hidden email]: Saturday, 13 September, 2008,
> 9:24 AM What is a mean score for a person? Upon what basis
> is the mean calculated? Whatis a case here, a person or
> something else? From: Johnny Amora
> [mailto:[hidden email]] Sent: Friday, September 12,
> 2008 7:21 PMTo: ViAnn Beadle;
> [hidden email]:
> Re: syntax to produce summary statistics I wrote:
> I have 28 scale variables with values ranging from 0 to
> 100%. The entire dataset has n=4000. I want that my output
> would have the following format:First column: Should
> contain the 28 variables appeared downward across rows. Thus
> this column contains 29 rows including the heading.Second
> Column: should contain the mean scores.Third column: should
> contain the standard deviation of scoresFourth column:
> Should contain the number of persons with >30 mean
> scores.Fifth or last Column: Should contain the mean of
> those persons with >30 meanscores. Then ViAnn wrote:
> What do you mean by the number of persons with >30 mean
> scores? And why doyou want it twice? Reply: There are
> 4000 persons, right? The mean scores range from 0 to
> 100%,right? Now, how many of the 4000 have mean scores of
> greater than 30 percent(>30%)? Hope this is clear.
> Johnny Johnny T. Amora Statistician,
> Center for Learning and Performance Assessment De La
> Salle-College of Saint Benilde Manila, Philippines ---
> On Sat, 9/13/08, ViAnn Beadle <[hidden email]>
> wrote: From: ViAnn Beadle
> <[hidden email]>Subject: Re: syntax to produce
> summary statisticsTo: [hidden email]:
> Saturday, 13 September, 2008, 9:05 AM What do you mean by
> the number of persons with >30 mean scores? And why doyou
> want it twice? -----Original Message-----From: SPSSX(r)
> Discussion [mailto:[hidden email]] On Behalf Of
> JohnnyAmoraSent: Friday, September 12, 2008 6:49 PMTo:
> [hidden email]: syntax to produce summary
> statistics Deal all, I have 28 scale variables with values
> ranging from 0 to 100%. The entire dataset has n=4000. I
> want that my output would have the following format:First
> column: Should contain the 28 variables appeared downward
> across rows. Thus this column contains 29 rows including the
> heading.Second
> Column: should contain the mean scores.Third column:
> should contain the standard deviation of scoresFourth
> column: Should contain the number of persons with >30
> mean scores.Fifth or last Column: Should contain the mean of
> those persons with >30 meanscores. I am pleased and
> thankful for any help about the syntax to produce such data.
> Thank you.Johnny New Email addresses available
> on Yahoo!Get the Email name you've always wanted on
> the new @ymail [hidden email] before someone else
> does!http://mail.promotions.yahoo.com/newdomains/ph/
> =======To manage your subscription to SPSSX-L, send a
> message [hidden email] (not to SPSSX-L), with
> no body text except thecommand. To leave the list, send the
> commandSIGNOFF SPSSX-LFor a list of commands to manage
> subscriptions, send the commandINFO REFCARD
> =====================To manage your subscription to SPSSX-L,
> send a message [hidden email] (not to
> SPSSX-L), with no body text except thecommand. To leave
> the list, send the commandSIGNOFF SPSSX-LFor a list of
> commands to manage subscriptions, send the commandINFO
> REFCARD _____
> <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>New
> Email names for you! Get the Email name you've always
> wanted on the new @ymail and @rocketmail.Hurry before
> someone else does! _____
> <http://sg.rd.yahoo.com/ph/mail/domainchoice/mail/signature/*http:/mail.promotions.yahoo.com/newdomains/ph/>Get
> your preferred Email name! Now you can @ymail.com and
> @rocketmail.com. ====================To manage your
> subscription to SPSSX-L, send a message
> [hidden email] (not to SPSSX-L), with no body
> text except thecommand. To leave the list, send the
> commandSIGNOFF SPSSX-LFor a list of commands to manage
> subscriptions, send the commandINFO REFCARD
>
>
> New Email addresses available on Yahoo!
> Get the Email name you've always wanted on the new
> @ymail and @rocketmail.
> Hurry before someone else does!
> http://mail.promotions.yahoo.com/newdomains/ph/
>
> =====================
> 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

New Email names for you!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!
http://mail.promotions.yahoo.com/newdomains/ph/

=======
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

NOTICE: This e-mail (and any attachments) may contain PRIVILEGED OR CONFIDENTIAL information and is intended only for the use of the specific individual(s) to whom it is addressed. It may contain information that is privileged and confidential under state and federal law. This information may be used or disclosed only in accordance with law, and you may be subject to penalties under law for improper use or further disclosure of the information in this e-mail and its attachments. If you have received this e-mail in error, please immediately notify the person named above by reply e-mail, and then delete the original e-mail. Thank you.

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