Is this a correct statistical analysis of a Likert-type scale rated by one group

Home Forums Methodspace discussion Is this a correct statistical analysis of a Likert-type scale rated by one group

Viewing 1 post (of 1 total)
  • Author
    Posts
  • #110284
    Hans
    Participant

    Hi everyone,

    I’m a novice in statistical analysis of empirical data and I was wondering if you experts could take a look at my project and tell me if I’m missing something and/or help me find the best approach.

    I’m interested in how closely people consider two concepts to be connected and which connection they consider the closest.

    I would like to ask a large group of people (n > 50) to rate on a 7 point Likert-type how close they consider the connection between, e.g.:
    yellow and joy
    red and joy
    blue and joy
    The scale is running from ‘no connection’ =1 to ‘immediate, i.e. extremely close connection’ = 7

    My approach is to calculate median and IQR for all responses, e.g.:
    yellow and joy -> Median: 5; IQR: 4
    red and joy -> Median: 6.5; IQR: 1.25
    blue and joy -> Median: 4.5; IQR: 2.25
    Thus, I would argue that red and joy are most closely connected and I would use them in further steps of my project.

    My first question is: Do I miss something?
    That is, do I need to calculate something else? For example, I don’t see how and if I should carry out a test of significance…

    My second question is:
    My data consists of the age of all respondents and the time they took for each response/rating, too.
    Is there a way to relate their rating score, their age and their response time for each item?

    Thank you so much,
    Hans

Viewing 1 post (of 1 total)
  • You must be logged in to reply to this topic.