Home > Statistics Every Writer Should Know > The Stats Board > Discusssion
Surveys
Message posted by Gill on October 3, 2000 at 12:00 AM (ET)
We quite often send out surveys asking people about themselves (giving us independent variables)
and scoring some dependent variable on an integer scale where 1=poor, 2=satisfactory, 3=good, 4=excellent.
Im assuming ANOVA is inappropriate since the dependent variable is not continuous.
Is there a way of looking at differences between the independent variables in these circumstances?
READERS RESPOND:
(In chronological order. Most recent at the bottom.)
Re: Surveys
Message posted by JG on October 4, 2000 at 12:00 AM (ET)
There are many things you can do as discussed in any introductory book of 'Statistics for the Social Sciences', etc. But first you must make sure that your scale or measuring instrument is valid and reliable. This involves making sure that you have a proper 'scale', etc. One of the many things that you can do is ask the same question in 2 or 3 different ways and compare the answer, etc. You also have to make sure you have a 'random' sample, etc. See some of the reference and links at (129.2.115.68/stats) for more details.
Your $5 contribution helps cover part the $500 annual cost of keeping this site online.