iSixSigma

Discrete or Continous Data ? CSAT SURVEY RESULTS

Six Sigma – iSixSigma Forums Old Forums General Discrete or Continous Data ? CSAT SURVEY RESULTS

Viewing 7 posts - 1 through 7 (of 7 total)
  • Author
    Posts
  • #40444

    Johnson
    Participant

    Hello-
    We have a customer satisfaction survey where the customers are required to answer 12 question on a scale of 1 to 5 (Question 1: is this discrete or continous data ?) and the overall satisfaction score is derived from averaging all the 12 questions (Question 2: is this discrete or continous ?)
    Please help.
     
     

    0
    #125559

    Ron
    Member

    This is a grey area. For purposes of analysis if this is a scale of 1 being bad and 10 being great you can analzyze this data as continuous.
     

    0
    #125568

    Darth
    Participant

    A scale of 1-5 is discrete no matter how you slice it.  Averaging the numbers doesn’t now make it continuous.  Best you can do is report out the number of people in each category or the percentage responding in each category.  As was suggested by ron, a wider scale can sometimes be dealt with as continuous but with the caveat that responses need to be spread across the scale.  If all the responses still fall in a limited number of categories it is still discrete.

    0
    #126192

    fsutculer
    Participant

    Hello,
    You actually use a scale which convert the district data to continous data!
    You can use this data as continous in your calculations.
    By the way, any district data can be converted to continous form by establishing a scale like you have. (Originally it is calle as likert scale or Bo Derek Scale. 
    Regards 

    0
    #126196

    Szentannai
    Member

    Hi,
    in statistics this is called ordinal data. Here’s a definition I found on the Web (http://www.cmh.edu/stats/definitions/ordinal.htm)

    Ordinal data are categorical data where there is a logical ordering to the categories. A good example is the Likert scale that you see on many surveys: 1=Strongly disagree; 2=Disagree; 3=Neutral; 4=Agree; 5=Strongly agree.
    While computation of a median is easily justified for ordinal data, some statisticians have reservations about computing a mean for ordinal data.
    Hope this helps
    Sandor
     

    0
    #126252

    Anand
    Participant

    The questionnaire definately captures “Qualitative” response which in turn gets converted into the “Quantitative” form. In my opinion, this is the conversion of the discrete data into continuous data, hence the data is necessarily continuous data and the analysis ccan be ccarried out for the same as that of continuous data only.

    0
    #126361

    Raafat
    Participant

    I believe this is discrete and it should not be averaged by any means because we are not dealing with numbers but with responses.

    0
Viewing 7 posts - 1 through 7 (of 7 total)

The forum ‘General’ is closed to new topics and replies.