The Student Room Group
Uni students - Complete our survey >>
Uni students - Complete our survey >>
Uni students - Complete our survey >>

Spss and ANOVA

I'm currently working on my dissertation but am struggling to decide what anova I am using. I have 3 groups of people, each using different methods to increase happiness. I am looking at the effectiveness of each by measuring happiness before and after.

Any advice would be really appreciated. Thankyou.
Original post by Hannahb426
I'm currently working on my dissertation but am struggling to decide what anova I am using. I have 3 groups of people, each using different methods to increase happiness. I am looking at the effectiveness of each by measuring happiness before and after.

Any advice would be really appreciated. Thankyou.

Personally I would compared the increase in happiness in each giving you just 3 columns of data as opposed to 6
You might be able to use a one way ANOVA for this but it needs to meet a few assumptions (that your data is normally distributed and the variance is also equal)
An ANOVA can only tell you that at least 1 group is significantly different from another. To find out which are significantly different you will need to follow up with a post hoc test e.g. Tukey test.
If your data is not normally distributed you could use it's non parametric equivalent the kruskal-wallis test
Reply 2
Avatar for Hannahb426
Hannahb426
OP
2
Original post by bits.of.bio
Personally I would compared the increase in happiness in each giving you just 3 columns of data as opposed to 6
You might be able to use a one way ANOVA for this but it needs to meet a few assumptions (that your data is normally distributed and the variance is also equal)
An ANOVA can only tell you that at least 1 group is significantly different from another. To find out which are significantly different you will need to follow up with a post hoc test e.g. Tukey test.
If your data is not normally distributed you could use it's non parametric equivalent the kruskal-wallis test

Thank you so much. I really appreciate the advice. 😊

Quick Reply

Related discussions

Latest

Trending

Trending

Articles for you