Okay, I'll take the bait...

Harris Interactive had a conference in Chicago not long ago where they presented on the regional/country differences in scale response among their Western European/Scandinavian panelists. My takeaway from the paper was...there are regional differences in the way respondents treat these scales.

This is bad news because you can't compare directly and you can't "normalize" across countries unless you know without question that the respondents are all getting exactly the same level of service/performance/product quality across countries. Someone has probably done some kind of research designed to derive a weighting scheme based on responses across countries evaluating a ubiquitous product or service, e.g. how sweet is Sweet 'n' Low, but that probably doesn't translate very well into other evaluations.

If you were designing a new survey, perhaps you could use the old "thermometer" and have them rate measures using 0 (freezing = bad) to 100 (boiling = good). But respondents from Finland would probably give 25 ratings for things they liked while the Greeks used 25 for things they didn't.

So we haven't answered the question, but maybe provoked a little thought...

Philip Moore Market Research Manager CarMax, the Auto Superstore

David Lindsay <spss2002_4@sdres earch.com> To Sent by: SPSSX-L@LISTSERV.UGA.EDU "SPSSX(r) cc Discussion" <SPSSX-L@LISTSERV Subject .UGA.EDU> Re: International differences in rating questions

06/28/2005 01:49 PM

Please respond to David Lindsay <spss2002_4@sdres earch.com>

Hi Anna

On 24 Jun 2005 at 16:52, A P wrote:

> I'm in the process of analyzing data from an international customer > loyalty/satisfaction study. In the study we ask the respondent to rate > their satisfaction (on a scale of 1-10) with a wide variety of different > experiences. > > Part of this analysis will include comparing the results between > countries. One of the questions I anticipate getting is how does > culture play into the differences we see.

My experience is that problems can occur in the translation of scales e.g. translating "slightly agree" into say Italian. In other words, nuances in word meanings have different interpretations when translated back into english.

> > Does anyone have any experience/information on how to handle cultural > differences when analyzing data from rating questions?

Also the way each country uses scales, some people seem to be better at using the whole of the scale even though the ends of the scales might be anchored using "strongly agree" and "strongly agree". Perhaps a useful way of analying the scales so you can make cross country comparisons would be to normalise the scales i.e. subtract the means and divide by the standard deviation.

I wonder what Philip Moore might say, he has some very sensible things to say about analysing likert sclaes.

Regards,

-- David