|
I am trying to convert scores from an old scale to a new scale. The old
scale is a 1 t 6. Where 1 is the minumum value. The new scale is 1 to 4. Where 1 is the minumun value. This scale is to be used for the HR evaluation of employees where 1 is poor and 4 is excellent. When using the old scale someone who received a 4.5 had to review their performance with a supervisor and 4.0 with the VP. I am trying to find the equivalent scoring for the 1 to 4 scale. Director Institutional Research |
|
If all you need is a simple linear conversion:
compute newscale=oldscale*(4/6). -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Dee Sent: Friday, September 07, 2007 2:26 PM To: [hidden email] Subject: converting scales I am trying to convert scores from an old scale to a new scale. The old scale is a 1 t 6. Where 1 is the minumum value. The new scale is 1 to 4. Where 1 is the minumun value. This scale is to be used for the HR evaluation of employees where 1 is poor and 4 is excellent. When using the old scale someone who received a 4.5 had to review their performance with a supervisor and 4.0 with the VP. I am trying to find the equivalent scoring for the 1 to 4 scale. Director Institutional Research |
|
In reply to this post by Dee-17
Oops. One of our statisticians (you can tell that I'm not one) pointed out that my solution would produce a minimum of 2/3, not 1. He suggested this instead:
Compute newscale=.4+.6*oldscale. -----Original Message----- From: Oliver, Richard Sent: Friday, September 07, 2007 2:42 PM To: 'Dee'; [hidden email] Subject: RE: converting scales If all you need is a simple linear conversion: compute newscale=oldscale*(4/6). -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Dee Sent: Friday, September 07, 2007 2:26 PM To: [hidden email] Subject: converting scales I am trying to convert scores from an old scale to a new scale. The old scale is a 1 t 6. Where 1 is the minumum value. The new scale is 1 to 4. Where 1 is the minumun value. This scale is to be used for the HR evaluation of employees where 1 is poor and 4 is excellent. When using the old scale someone who received a 4.5 had to review their performance with a supervisor and 4.0 with the VP. I am trying to find the equivalent scoring for the 1 to 4 scale. Director Institutional Research |
|
In reply to this post by Dee-17
So in the new scale a value of 3 is comparable to 4.5 in the old scale
and a score of 2.67 is comparable to a value of 4 in the old scale. Melissa -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Oliver, Richard Sent: Friday, September 07, 2007 2:42 PM To: [hidden email] Subject: Re: [SPSSX-L] converting scales If all you need is a simple linear conversion: compute newscale=oldscale*(4/6). -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Dee Sent: Friday, September 07, 2007 2:26 PM To: [hidden email] Subject: converting scales I am trying to convert scores from an old scale to a new scale. The old scale is a 1 t 6. Where 1 is the minumum value. The new scale is 1 to 4. Where 1 is the minumun value. This scale is to be used for the HR evaluation of employees where 1 is poor and 4 is excellent. When using the old scale someone who received a 4.5 had to review their performance with a supervisor and 4.0 with the VP. I am trying to find the equivalent scoring for the 1 to 4 scale. Director Institutional Research PRIVILEGED AND CONFIDENTIAL INFORMATION This transmittal and any attachments may contain PRIVILEGED AND CONFIDENTIAL information and is intended only for the use of the addressee. If you are not the designated recipient, or an employee or agent authorized to deliver such transmittals to the designated recipient, you are hereby notified that any dissemination, copying or publication of this transmittal is strictly prohibited. If you have received this transmittal in error, please notify us immediately by replying to the sender and delete this copy from your system. You may also call us at (309) 827-6026 for assistance. |
|
The problem with using a simple linear conversion is that, depending on the two scales, neither the scale end-points nor the standard scores (z-scores) will be maintained.
Although you don't say it, I'm assuming you are talking about averages across a number of ratings, so maintaining z-scores is important. A simple linear conversion as suggested would underestimate the mean score, leaving more employees vulnerable to review. I suggest using this formula: New score = (old score - old scale midpoint)*(new range/old range) + new scale midpoint. For instance, the converted score on a 4-point scale for a value of 3 on a 6-point scale would be (3-3.5)*(3/5)+2.5 = 2.2 As opposed to 3*4/6 = 2 using the simple, linear transformation suggested below. Using the formula above and converting from 6- to 4- point scale 1=1 2=1.6 3=2.2 4=2.8 5=3.4 6=4 King Douglas American Airline Customer Research elissa Ives <[hidden email]> wrote: So in the new scale a value of 3 is comparable to 4.5 in the old scale and a score of 2.67 is comparable to a value of 4 in the old scale. Melissa -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Oliver, Richard Sent: Friday, September 07, 2007 2:42 PM To: [hidden email] Subject: Re: [SPSSX-L] converting scales If all you need is a simple linear conversion: compute newscale=oldscale*(4/6). -----Original Message----- From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Dee Sent: Friday, September 07, 2007 2:26 PM To: [hidden email] Subject: converting scales I am trying to convert scores from an old scale to a new scale. The old scale is a 1 t 6. Where 1 is the minumum value. The new scale is 1 to 4. Where 1 is the minumun value. This scale is to be used for the HR evaluation of employees where 1 is poor and 4 is excellent. When using the old scale someone who received a 4.5 had to review their performance with a supervisor and 4.0 with the VP. I am trying to find the equivalent scoring for the 1 to 4 scale. Director Institutional Research PRIVILEGED AND CONFIDENTIAL INFORMATION This transmittal and any attachments may contain PRIVILEGED AND CONFIDENTIAL information and is intended only for the use of the addressee. If you are not the designated recipient, or an employee or agent authorized to deliver such transmittals to the designated recipient, you are hereby notified that any dissemination, copying or publication of this transmittal is strictly prohibited. If you have received this transmittal in error, please notify us immediately by replying to the sender and delete this copy from your system. You may also call us at (309) 827-6026 for assistance. |
| Free forum by Nabble | Edit this page |
