|Date: ||Fri, 12 Mar 2010 08:18:09 -0500|
|Reply-To: ||Dave Taber <email@example.com>|
|Sender: ||"SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>|
|From: ||Dave Taber <firstname.lastname@example.org>|
|Subject: ||Re: Net Promoter Score syntax|
|Content-Type: ||text/plain; charset=ISO-8859-1|
this is a previous post i sent out in 2007 to Tanya - as for the NP
score itself, i'm not a big fan -- your question is referenced toward
don't know if there is an answer to your question but when you
calculate the net promoter (NP) score, the z-test is not applicable.
The reason for this is that when when you track this measure you may
be double-counting a change in the proportion of respondents. This is
because when the proportion who answered 9 or 10 goes up by 1 pct
point you will be doubling that increase if the proportion who
answered 1 to 6 decreased by 1 pct point.
The resulting NP score is actually not a proportion -- it's just a
calculated score. You would expect much greater variation with a NP
score than a top 2-box percentage.
on a separate note, an easy way to track net promoter scores in spss
is to recode 9-10 to +100, 7-8 to 0, and 1-6 (or 0-6) to -100 -- then
just compare the mean of the new variable over over time.
you might want to check with the company that advocates this technique
http://www.satmetrix.com/netpromoter/index.htm to see what they say
about statistical differences over time
On Fri, Mar 12, 2010 at 6:04 AM, Mark Webb <email@example.com> wrote:
> Some market researchers compute a score called Net Promoter Score.
> I'm trying to write syntax for this score but am struggling.
> Has anyone does this? - any assistance will be appreciated.
> NPS is computed from an 11 point scale [0-10] of recommendation where 10
> = Extremely Likely to Recommend.
> The 11 point scale is reduced to 3 points
> 0-6 = Detractors
> 7-8 = Passives
> 9-10 = Promoters
> The NPS = %Promoters - %Detractors
> An example -
> Detractors 10%
> Passives 30%
> Promoters 60%
> NPS = 60-10=40
> The only data I have is a rating from each respondent on the 0-10
> scale-one variable.
> I'm struggling to compute the percentages into new variables so that I
> can subtract them.
> As the percentages will vary if a filter is applied it will be necessary
> to recalculate for each new filter.
> Mark Webb
> Line +27 (21) 786 4379
> Cell +27 (72) 199 1000
> Fax to email +27 (86) 5513075
> Skype webbmark
> Email firstname.lastname@example.org
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@LISTSERV.UGA.EDU (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
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
For a list of commands to manage subscriptions, send the command