x Turn on thread page Beta
 You are Here: Home

# Which spss analysis should I use? watch

1. Hi,
I conducting an experiment 2x2 design and know that I should probably use a ANOVA analysis but not sure of the type.

There are two IV's with two levels and one DV

Four different participant groups (independent groups) with the following exposure to the conditions
1. IV1- level1 with IV2 L1then IV2 L2
2. IV 1 - L1 with IV2 L2 then IV2 L1
3. IV1 - L2 with IV2 L1then IV2 L2
3. IV1 - L2 with IV2 L2 then IV2 L1

Hope this makes sense. I did think I needed a one way independent ANOVA but I do t think this is correct.

Any help very very appreciated.

Thanks
2. My stats is INSANELY rusty, but sounds about right. ANOVA... and then post-hoc analysis?
Hope my message acts as a BUMP at least :P
Laerds website should clear things up, as says all the analysis types and examples of such studies.
3. Thank you for your help.

I also wondered do I need to check parametric assumptions with all types of data?
4. (Original post by holly2587374)

I also wondered do I need to check parametric assumptions with all types of data?
My ANOVA is a bit rusty too. Let me get you straight: your using a between subjects design, with two conditions, with two levels each, meaning that there are overall four possible groups that people could fall into?

You can do a two way ANOVA which will give you results for the two effects without the need for post hoc analyses (which are required when you have more than 2 levels). You could run four seperate one-way ANOVAs, however this analysis would have less statistical power as in the two-way ANOVA your examining the effect of each condition whilst controlling for variability caused by the alternate condition, which also allows you to pool all the data together into a single analysis. FYI you could run the same analysis using multiple regression give you exactly the same result. Main things to look out for are heteroscedasticity and normality (although the larger the sample size the less normality matters).
5. I think I need a two factor mixed ANOVA as yes there are four groups but the first IV is between subjects and the second IV is within subjects?

It sounds like you are saying that I do need to test parametric assumptions. So am i right in thinking if they are not met that I should analyse data differently? Is there an alternative test for a factor anova?
6. (Original post by holly2587374)
I think I need a two factor mixed ANOVA as yes there are four groups but the first IV is between subjects and the second IV is within subjects?

It sounds like you are saying that I do need to test parametric assumptions. So am i right in thinking if they are not met that I should analyse data differently? Is there an alternative test for a factor anova?
Oh well if one factor is within subjects then it would be a mixed ANOVA yes. I think there is a type of ANOVA that is robust to assumptions of heteroscedasticity and normality, however i'm not sure if SPSS provides all of them. You can normally fix normality with transforming the data!

TSR Support Team

We have a brilliant team of more than 60 Support Team members looking after discussions on The Student Room, helping to make it a fun, safe and useful place to hang out.

This forum is supported by:
Updated: March 16, 2016
Today on TSR

### Any tips for freshers...

who are introverts?

### More snow?!

Discussions on TSR

• Latest
Poll
Useful resources

Can you help? Study Help unanswered threadsStudy Help rules and posting guidelines

## Groups associated with this forum:

View associated groups
Discussions on TSR

• Latest

The Student Room, Get Revising and Marked by Teachers are trading names of The Student Room Group Ltd.

Register Number: 04666380 (England and Wales), VAT No. 806 8067 22 Registered Office: International House, Queens Road, Brighton, BN1 3XE