SPSSX Discussion

How get rid of meaningless digits in MEANS output?

Classic

List

Threaded

6 messages Options

Eero Olli

How get rid of meaningless digits in MEANS output?

Hello to you all,

I am calculating some means often, and I would like to get rid of some extra digits.

This is the output from MEANS
A B
Mean 6,60 9,86
N 3098 436

This is what I would like to have
A B
Mean 7 10
N 3098 436

Is there a way to reduce the number of digits (round) in the result to whole numbers in the syntax? I have tried various commands but they affect the variables themselves, not the result of the means procedure.

Sincerely,
Eero Olli

_________________________________
Rådgiver Eero Olli
Likestillings- og diskrimineringsombudet
[hidden email] +47 24055951
Postboks 8048 Dep, N-0031 Oslo

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

Hector Maletta

Re: How get rid of meaningless digits in MEANS output?

The mean has the number of decimals established in the variable's format.
Just change the format before asking for the mean. For instance, for getting
no decimals:

FORMAT A B (F8.0).
MEANS A B /CELLS MEAN N.
The F8.0 implies eight visible places (including the decimal point), with
zero decimals. F8.2 would imply 8 places and 2 decimals, i.e. up to 5
integers, one place for the decimal point, and two decimals.
The FORMAT command does not affect the internal precision of the mean, or
any other result, which is always the same (about 20 decimals), but only the
appearance of the variable in the data editor and its statistics in the
output.
Hector
-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Eero Olli
Sent: 24 January 2008 20:48
To: [hidden email]
Subject: How get rid of meaningless digits in MEANS output?

Hello to you all,

I am calculating some means often, and I would like to get rid of some extra
digits.

This is the output from MEANS
A B
Mean 6,60 9,86
N 3098 436

This is what I would like to have
A B
Mean 7 10
N 3098 436

Is there a way to reduce the number of digits (round) in the result to whole
numbers in the syntax? I have tried various commands but they affect the
variables themselves, not the result of the means procedure.

Sincerely,
Eero Olli

_________________________________
Rådgiver Eero Olli
Likestillings- og diskrimineringsombudet
[hidden email] +47 24055951
Postboks 8048 Dep, N-0031 Oslo

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

Eero Olli

SV: How get rid of meaningless digits in MEANS output?

Thanks for your reply.

I should have written in my orginal mail that use the FORMATS
and my variables are already in F2.0 format. I have also tried the PRINT FORMAT or WRITE FORMAT but the the output format of the MEANS command does not change.

FORMATS A B (F2.0).
MEANS
TABLES=A B BY C
/CELLS MEAN COUNT MIN MAX .

I am running SPSS 15.0 and this behavior goes ways back, if I remember correctly.

Best,
Eero

_________________________________
Rådgiver Eero Olli
Likestillings- og diskrimineringsombudet
[hidden email] +47 24055951
Postboks 8048 Dep, N-0031 Oslo

-----Opprinnelig melding-----
Fra: Hector Maletta [mailto:[hidden email]]
Sendt: 24. januar 2008 16:27
Til: Eero Olli; [hidden email]
Emne: RE: How get rid of meaningless digits in MEANS output?

The mean has the number of decimals established in the variable's format.
Just change the format before asking for the mean. For instance, for getting no decimals:

FORMAT A B (F8.0).
MEANS A B /CELLS MEAN N.
The F8.0 implies eight visible places (including the decimal point), with zero decimals. F8.2 would imply 8 places and 2 decimals, i.e. up to 5 integers, one place for the decimal point, and two decimals.
The FORMAT command does not affect the internal precision of the mean, or any other result, which is always the same (about 20 decimals), but only the appearance of the variable in the data editor and its statistics in the output.
Hector
-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Eero Olli
Sent: 24 January 2008 20:48
To: [hidden email]
Subject: How get rid of meaningless digits in MEANS output?

Hello to you all,

I am calculating some means often, and I would like to get rid of some extra digits.

This is the output from MEANS
A B
Mean 6,60 9,86
N 3098 436

This is what I would like to have
A B
Mean 7 10
N 3098 436

Is there a way to reduce the number of digits (round) in the result to whole numbers in the syntax? I have tried various commands but they affect the variables themselves, not the result of the means procedure.

Sincerely,
Eero Olli

_________________________________
Rådgiver Eero Olli
Likestillings- og diskrimineringsombudet
[hidden email] +47 24055951
Postboks 8048 Dep, N-0031 Oslo

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

ViAnn Beadle

Re: How get rid of meaningless digits in MEANS output?

Most procedures within SPSS add 2 decimal digits to the mean displayed since
most users would think those digits significant. Many procedures within SPSS
are able to calculate the MEAN of a variable and some of them allow you to
explicitly provide a format for the output. Check out REPORT (which produces
ordinary text output and not pivot table output), TABLES, or CTABLES. If
you're really determined, you can also use the AGGREGATE command to create a
new file of means as variables which you can then define PRINT FORMATS for
and use LIST CASES to list them.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Eero Olli
Sent: Thursday, January 24, 2008 8:47 AM
To: [hidden email]
Subject: SV: How get rid of meaningless digits in MEANS output?

Thanks for your reply.

I should have written in my orginal mail that use the FORMATS
and my variables are already in F2.0 format. I have also tried the PRINT
FORMAT or WRITE FORMAT but the the output format of the MEANS command does
not change.

FORMATS A B (F2.0).
MEANS
TABLES=A B BY C
/CELLS MEAN COUNT MIN MAX .

I am running SPSS 15.0 and this behavior goes ways back, if I remember
correctly.

Best,
Eero

_________________________________
Rådgiver Eero Olli
Likestillings- og diskrimineringsombudet
[hidden email] +47 24055951
Postboks 8048 Dep, N-0031 Oslo

-----Opprinnelig melding-----
Fra: Hector Maletta [mailto:[hidden email]]
Sendt: 24. januar 2008 16:27
Til: Eero Olli; [hidden email]
Emne: RE: How get rid of meaningless digits in MEANS output?

The mean has the number of decimals established in the variable's format.
Just change the format before asking for the mean. For instance, for getting
no decimals:

FORMAT A B (F8.0).
MEANS A B /CELLS MEAN N.
The F8.0 implies eight visible places (including the decimal point), with
zero decimals. F8.2 would imply 8 places and 2 decimals, i.e. up to 5
integers, one place for the decimal point, and two decimals.
The FORMAT command does not affect the internal precision of the mean, or
any other result, which is always the same (about 20 decimals), but only the
appearance of the variable in the data editor and its statistics in the
output.
Hector
-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Eero Olli
Sent: 24 January 2008 20:48
To: [hidden email]
Subject: How get rid of meaningless digits in MEANS output?

Hello to you all,

I am calculating some means often, and I would like to get rid of some extra
digits.

This is the output from MEANS
A B
Mean 6,60 9,86
N 3098 436

This is what I would like to have
A B
Mean 7 10
N 3098 436

Is there a way to reduce the number of digits (round) in the result to whole
numbers in the syntax? I have tried various commands but they affect the
variables themselves, not the result of the means procedure.

Sincerely,
Eero Olli

_________________________________
Rådgiver Eero Olli
Likestillings- og diskrimineringsombudet
[hidden email] +47 24055951
Postboks 8048 Dep, N-0031 Oslo

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

Johnny Amora

Constructing frequency tables for 5-point scale items

Hi everyone,

Suppose I have 10-item questionnaire (the items are
Q1, Q2, ...,Q10). Suppose further that each item in
the questionnaire would require the 100 persons to
rate using 5-point disagree/agree scale coded as
1=strongly disagree; 2=disagree; 3= slightly agree;
4=agree; and 5=strongly agree.

To summarize the collected data, the following 11 by 7
matrix format is required, where the first row
represents the column heading. The first columns are
the items; the 2nd to 6th columns are the frequency
counts of the responses; and the last column the
arithmetic mean.

items 1 2 3 4 5 mean
Q1
Q2
Q3
.
.
.
Q10

Are there spss codes that would produce such output?
Your help is highly solicited.
Thank you.

Johnny

____________________________________________________________________________________
Be a better friend, newshound, and
know-it-all with Yahoo! Mobile. Try it now. http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ

=====================
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: Constructing frequency tables for 5-point scale items

Here you go--this example does 5 variables, you can extrapolate. Note that
CTABLES is not part of the base.

CTABLES
/VLABELS VARIABLES=v1 v2 v3 v4 v5 DISPLAY=DEFAULT
/TABLE v1 [COUNT F40.0 TOTALS[MEAN]] + v2 [COUNT F40.0 TOTALS[MEAN]]
+ v3 [COUNT F40.0 TOTALS[MEAN]] + v4 [COUNT F40.0 TOTALS[MEAN]]
+ v5 [COUNT F40.0 TOTALS[MEAN]]
/CLABELS ROWLABEL=OPPOSITE
/CATEGORIES VARIABLES=v1 v2 v3 v4 v5 ORDER=A KEY=VALUE EMPTY=INCLUDE
TOTAL=YES.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
John Amora
Sent: Friday, January 25, 2008 6:24 AM
To: [hidden email]
Subject: Constructing frequency tables for 5-point scale items

Hi everyone,

Suppose I have 10-item questionnaire (the items are
Q1, Q2, ...,Q10). Suppose further that each item in
the questionnaire would require the 100 persons to
rate using 5-point disagree/agree scale coded as
1=strongly disagree; 2=disagree; 3= slightly agree;
4=agree; and 5=strongly agree.

To summarize the collected data, the following 11 by 7
matrix format is required, where the first row
represents the column heading. The first columns are
the items; the 2nd to 6th columns are the frequency
counts of the responses; and the last column the
arithmetic mean.

items 1 2 3 4 5 mean
Q1
Q2
Q3
.
.
.
Q10

Are there spss codes that would produce such output?
Your help is highly solicited.
Thank you.

Johnny

____________________________________________________________________________
________
Be a better friend, newshound, and
know-it-all with Yahoo! Mobile. Try it now.
http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ

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