The Student Room Group
<a https://www.thestudentroom.co.uk/showthread.php?t=7467335'> Year 12s: what will be the first way you research your future options? >>
<a https://www.thestudentroom.co.uk/showthread.php?t=7467335'> Year 12s: what will be the first way you research your future options? >>
<a https://www.thestudentroom.co.uk/showthread.php?t=7467335'> Year 12s: what will be the first way you research your future options? >>

normality and non-parametric

Basically i've collected my results and my IV tests: estimates of speed using different leading words. when testing normality for all responses it's non-significant p>.05 thus normal yet when I test it for each experimental group, one group is normal and the other is not.
Do I run a non-parametric test then or do I use the overall normality result and run a parametric??

please help!! :smile:
(edited 12 years ago)
Reply 1
Avatar for gadget-Geek
gadget-Geek
OP
**bump**
Do you know what's causing the non-normality? Check for outliers in the group that's the problem & if you find any, try removing them to see if that makes a difference (although depending on the nature of your research question/hypotheses it might not make sense or be necessary to remove them). Generally speaking though, if outliers are the issue then removing them should allow you to use parametric tests :smile:

Quick Reply

Related discussions

Latest

Trending

Trending

Articles for you