+ Reply to Thread
Results 1 to 1 of 1

Thread: using Mann Whitney

  1. #1
    Points: 46, Level: 1
    Level completed: 92%, Points required for next Level: 4

    Thanked 0 Times in 0 Posts

    using Mann Whitney

    I am trying to analyze a survey that asked students to respond to questions e.g. “In my opinion, the economic system in the US leads to an unfair distribution of income” by indicating their opinion using a Likert scale. The number of respondents are 280. The answers are broken down by gender. Looking at the answers for a question, when using vassarstat online, the mean rank for sample A and B are also returned (130.9 for A; and 156 for B) when the result is significant at p < .05. Can I use this to indicate that in group B higher % of students answered agree and strongly agreed ( agree=4; strongly agree=5) with the statement posed?

    Looking at the more detailed statistics calculated by http://www.socscistatistics.com/test.../Default2.aspx
    Result Details

    Sample 1
    Sum of ranks: 22648.5
    Mean of ranks: 130.92
    Expected sum of ranks: 24306.5
    Expected mean of ranks: 140.5
    U-value: 10913.5
    Expected U-value: 9255.5

    Sample 2
    Sum of ranks: 16691.5
    Mean of ranks: 156
    Expected sum of ranks: 15033.5
    Expected mean of ranks: 140.5
    U-value: 7597.5
    Expected U-value: 9255.5

    Do I need to report the U values?
    Last edited by Zsuzsa; 12-28-2016 at 09:17 AM.

+ Reply to Thread


Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats