+ Reply to Thread
Results 1 to 3 of 3

Thread: Hypotheses testing

  1. #1
    Points: 1,755, Level: 24
    Level completed: 55%, Points required for next Level: 45

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Hypotheses testing



    Hi I'm doing a dissertation and looking for some advice on which statistical tests to perform on the data I collect during an experiment.

    The experiment will involve 20 - 40 users performing tasks on a web site. Each user is required to perform every task. Tasks are divided into 5 sessions each consisting of approx 10 tasks. The order in which sessions 1 and 2 are presented will be reversed for half the test users, as will sessions 3 and 4. The experiment will produce the following quantitative data; task duration, number of mouse clicks required to perform the task, and the number of succssfull tasks completed.

    After each session users are required to complete a satisfaction questionnaire. The answers will be collected using a 5 point likert scale; stronly disagree, disagree, neither agree or disagree etc.. I will record the response on a scale of 1 to 5, 1 representing strongly disagree, and 5 representing strongly agree.
    Sample
    The test users will be recruited from my friends and family, I will in so far as possible, try to use a balanced mix of sex, internet browsing experience and age.

    Please see attached excel spreadsheet containing a sample of what the data should look like.

    Any sugeestions would be much appreciated.
    Attached Files

  2. #2
    Points: 2,020, Level: 27
    Level completed: 14%, Points required for next Level: 130

    Location
    Leeds, UK
    Posts
    50
    Thanks
    4
    Thanked 0 Times in 0 Posts
    What is the purpose of the experiment ?

  3. #3
    Points: 1,755, Level: 24
    Level completed: 55%, Points required for next Level: 45

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Hi and thanks for quick response.

    The experiment seeks to validate Web site 'usability' guidelines. User performance (time, success rate, mouse clicks required to complete tasks) and satisfaction (survey using likert scale) are compared from Web sites following the guidelines against Web sites that don't.

+ Reply to Thread

Similar Threads

  1. testing hypotheses
    By messianic in forum Probability
    Replies: 5
    Last Post: 07-14-2010, 05:20 PM
  2. Hypotheses Testing
    By anna_n10 in forum Statistics
    Replies: 0
    Last Post: 03-19-2009, 07:14 AM
  3. Replies: 3
    Last Post: 12-16-2008, 12:41 AM
  4. Testing Hypotheses/Estimation Question
    By Chibi in forum Statistics
    Replies: 1
    Last Post: 10-21-2008, 08:02 AM
  5. What do you think of my hypotheses?
    By georgemac in forum Statistics
    Replies: 0
    Last Post: 05-01-2008, 05:42 AM

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