Reverse scaling for continuous variables

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

Reverse scaling for continuous variables

Susan Seibold-Simpson
Hi all-
I'm new to this list and haven't figured out how to work the archives yet, so I apologize if this has been previously discussed.

I'm looking for assistance on how to reverse code continuous variables with many values.  For example, median income levels from the Bureau of Census is one of the variables I need to reserve scale.  I know how to reverse code categorical variables, but haven't figured out how to do variables with a large amount of variables.

Thanks for your help.

Susan Seibold-Simpson
MS, MPH, APRN, FNP
Doctoral Candidate
University of Rochester, School of Nursing
Reply | Threaded
Open this post in threaded view
|

Re: Reverse scaling for continuous variables

Justin Black
Hi Susan,

If you multiply your income variable by -1, the absolue value of, e.g., a
correlation coefficient would stay the same but the direction would flip.
Would that give you what you're looking for?

COMPUTE incomeRev = income*-1 .

Best,

--Justin

--
Justin Black
Doctoral Student
Industrial-Organizational Psychology
Baruch College, CUNY

On 11/18/06, Susan Seibold-Simpson <[hidden email]> wrote:

>
> Hi all-
> I'm new to this list and haven't figured out how to work the archives yet,
> so I apologize if this has been previously discussed.
>
> I'm looking for assistance on how to reverse code continuous variables
> with many values.  For example, median income levels from the Bureau of
> Census is one of the variables I need to reserve scale.  I know how to
> reverse code categorical variables, but haven't figured out how to do
> variables with a large amount of variables.
>
> Thanks for your help.
>
> Susan Seibold-Simpson
> MS, MPH, APRN, FNP
> Doctoral Candidate
> University of Rochester, School of Nursing
>