Normalizing scores

[Garry Gelade]

Mike

Imagine you have 100 people who responding to the same item twice, once
using the first scale and once using the second scale.  You then have two
sets of scores, for that item, call them S1 and S2.  You regress S1 on S2
(or vice-versa) and solve the regression equation:

S1 = B0 + B1* S2

Knowing the values of B0 and B1 You can now convert any score S2 into the
corresponding S1 score. You can apply this equation to your original data
(or any subset thereof) and say what the score would have been using the
other scale.

You would need to do this for all the items you wish to convert, so one way
to do it would be two surveys. You would need to identify the respondents so
you can match them up to conduct the regressions, and you'd probably want to
reverse the order of presentation for half of the participants to eliminate
order effects.

Hope this is clear.

Regards

Garry



-----Original Message-----
From: MR [mailto:[hidden email]]
Sent: 28 April 2013 15:57
To: Garry Gelade
Cc: [hidden email]
Subject: Re: Normalizing scores

Garry,

Can you explain me more on applying regression results to rescore? I have
not come across such technique and would appreciate if you can throw some
light.

Once I am done with this issue on hand, I am going to conduct a seperate
study to measure the impact and will be more than happy to share the results
with you all.


On 2013-04-28, at 7:30 AM, "Garry Gelade" <[hidden email]>
wrote:

> Mike,
>
> The only thing I can think of is to run the survey on a subset of
> individuals (preferably a stratified random sample) using both forms
> of the scale. Then regress one score on the other. You can then apply
> the regression results to rescore your previous survey into the
> alternative scale form.
>
> Garry Gelade
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf
> Of MR
> Sent: 28 April 2013 01:23
> To: [hidden email]
> Subject: Normalizing scores
>
> Team,
>
> I have one problem on my hand and am running out of options on which
> statistics to use in SPSS. First, I know that the what I want to do is
> not advisable but trust me, I have fought my battle on this. This is
> what I want to achieve:
>
> Issue: We did wave 1 survey using 5-point satisfaction scale. The
> second wave was conducted using 5-point agreement scale. Expectedly,
> top-box scores from agreement scale when compared to top-box score of
> satisfaction scale was low by 10% points. For e.g., agreement scale
> top box in wave 2 came out as 50% while wave 1 it was 60%.
>
> Goal: I have compared the historical data and conclude that score
> difference is purely due to scale change. However, i want to normalize
> the wave 2 score so that I can compare with wave 1. I know this is not
> advisable but I have to do this. I googled but could not find any
> statistics that helps to normalize the scores - indeed I don't know
> where to begin. I need a scientific method to normalize the scores so
> that they are comparable. I don't want to conclude that performance
> dropped by 10% just because scale changed.
>
> Your wisdom and help is very much required.
>
> Thanks,
> Mike
>
> =====================
> 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