Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie

Comreg survey - is this a misprint?

Options
  • 14-08-2010 9:47pm
    #1
    Fogmatic
    Registered Users Posts: 986 ✭✭✭


    I read (Irish Times, Aug. 7th) some results of a Comreg survey (published Aug. 6th).
    71% of respondants had a fixed line, 96% owned a mobile, 60% had contacted their fixed-line provider about problems, and 90% were satisfied with the service received (hmm.... not sure about that).
    It goes on to say that the survey was of more than... (this is where it got really dubious)...1,000 people, aged between 15 and 74.

    Unless '1,000' is a misprint, it could be straight out of Ben Goldacre's 'Bad Science' campaign. How did they select this 1,000 people? How did they make sure they were representative of the population as a whole? Surely doing the selection properly would need more work/money than simply using a bigger sample? Was it of people who took the trouble to fill in a form/ spend time on the phone because they still believe it'll make a difference? Was the questionnaire any better designed than some council/government ones I've seen?

    I also wondered what 15-to-17 year old wouldn't be satisfied by the service received via their parents' phone line, what with not having to pay for it, or do any of the work getting faults fixed. And I imagine the senior end of the survey includes people receiving free line rental; it doesn't always feel right to declare dissatisfaction with a free service.

    Or am I just getting too cynical?


Comments

  • Options
    #2
    BurnsCarpenter
    Registered Users Posts: 552 ✭✭✭BurnsCarpenter


    1007 people surveyed according to comreg's own doc:

    http://www.comreg.ie/_fileupload/publications/ComReg_1062r.pdf

    The methodology section says the accuracy is +/- 3%.
    I'm not really well up on statistics. Isn't that size of sample similar enough to pre-election polls?


  • Options
    #3
    watty
    Registered Users Posts: 32,417 ✭✭✭✭watty


    The trick is how do you select the 1007?

    saying it's 3% means nothing without details, but I have not read the report yet.

    How you ask the questions and the questions missing are important?

    The 71% shows a bais as less than 66% have a fixed line and 1/3rd of those is Welfare paid.

    I'll look at it later.


Advertisement