Rounding Options

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

Rounding Options

Courtney M. Cronley
Hi Everyone,

I have a question about syntax for rounding up variable values. I ran a multiple imputation, and the resultant imputed data sets have variable values that are decimals. I need the values to be whole integers for an ordinal variable. For instance, I have a four-point ordinal variable, and values between 3.5 and 4 need to be rounded up to 4. How can I round up values for these variables? All I can find on the help function is an option to round up single values, but I have tens of values that need to be rounded up. This option would take forever.

Thanks!

Courtney

Courtney Cronley, Ph.D.
Postdoctoral Associate
Center of Alcohol Studies
Rutgers University
[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: Rounding Options

Julius Sim
  Hi,

There is SPSS syntax here that will specifically round up non-integer
values:

http://www.tek-tips.com/viewthread.cfm?qid=1118740&page=5

There is also a function in MS Excel - it's called ROUNDUP. The Excel
function certainly works, but I had problems with the SPSS syntax
(probably my fault, not the syntax's!)

Best wishes,

Julius




On 22/09/2010 17:17, Courtney M. Cronley wrote:

> Hi Everyone,
>
> I have a question about syntax for rounding up variable values. I ran a multiple imputation, and the resultant imputed data sets have variable values that are decimals. I need the values to be whole integers for an ordinal variable. For instance, I have a four-point ordinal variable, and values between 3.5 and 4 need to be rounded up to 4. How can I round up values for these variables? All I can find on the help function is an option to round up single values, but I have tens of values that need to be rounded up. This option would take forever.
>
> Thanks!
>
> Courtney
>
> Courtney Cronley, Ph.D.
> Postdoctoral Associate
> Center of Alcohol Studies
> Rutgers University
> [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

=====================
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: Rounding Options

Maguin, Eugene
In reply to this post by Courtney M. Cronley
Courtney,

The spss function to use is rnd(x), where x is a numeric value. Since you
have many variables that need to be rounded, I'd suggest using the do repeat
command as in

Do repeat a=x1 to x5 y4 to y24.
+  compute a=rnd(a).
end repeat.

Gene Maguin



-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Courtney M. Cronley
Sent: Wednesday, September 22, 2010 12:18 PM
To: [hidden email]
Subject: Rounding Options

Hi Everyone,

I have a question about syntax for rounding up variable values. I ran a
multiple imputation, and the resultant imputed data sets have variable
values that are decimals. I need the values to be whole integers for an
ordinal variable. For instance, I have a four-point ordinal variable, and
values between 3.5 and 4 need to be rounded up to 4. How can I round up
values for these variables? All I can find on the help function is an option
to round up single values, but I have tens of values that need to be rounded
up. This option would take forever.

Thanks!

Courtney

Courtney Cronley, Ph.D.
Postdoctoral Associate
Center of Alcohol Studies
Rutgers University
[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

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