Scribd
Upload
9 views16 pages

LEC Week 8b Factorial ANOVA

psychology stats

Uploaded by

saradump16
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
9 views16 pages

LEC Week 8b Factorial ANOVA

psychology stats

Uploaded by

saradump16
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 16

An OMNIBUS Analysis

Everyone takes the drugs. Thus, I get rid of the underlying differences.
Factorial = When you are using more than one factor/more than one IV.
We are looking for 3 things
 1 for each IV so (2) and then 1 for the interruption of them (if it
depends on the combination)
 Each of them gives me a score of what is the pain relief.
 You can see the combination of the two variables.

 Interaction: the effects of the variables influencing one another.


 1. Main effect of the type of pain
- Test for pain relief for all the people with each groups when mashed
together (Arthritis all together) & (Muscle pain all together)
- So, for now we ignore the type of drug they take: “COLLAPSING”.

 2. Main effect of drug


- Collapsing: So, ignoring what type of pain people have
 If you find a main effect, what is the next step?
- Post hoc test: “Pair wise** comparison”
HOWEVER: WE ONLY DO A POST HOC TEST ONLY WHEN WE HAVE 3 GROUPS.
 Looking at different groupings of means.
 If there is an interaction effect then you can conclude that; “The effect
of the drug, depends on the type of pain you have.”

 If we can an opposition of patterns (when you ‘eye it up’), there we


know that there is an interaction before we even mathematically test it
out.
 A crossing pattern: An Interaction
Look at BRIGHTSPACE table picture
 8.15 (ARTHIRITIS) vs 5.8 (MUSCLE)
 df Total ‘n’ (18) – 1 = 17
In-class Table for conclusion in APA.

Hypothesis Test
 You will have 3 hypotheses as you have 3 tests.
Table in class.
 No need for a Post Hoc test because there is only 2 groups.
REMINDER ASK HER HOW TO DO THIS WITH BAR GRAPH.
 I have two variables here Letter (A vs B) & Colour (blue vs red) and
Interaction.
 Understand statements and what they mean. ON EXAM YOU WILL BE
ASKED WHAT A STATEMENT MEANS.
In -class table: In a bar graph how to make line graph.

On average Blue is Higher > than Red.

If I’m A, Blue is better than red, but if I’m B then Red is better than blue.
 Factorial Design: Harder to interpret but more generalizable (realistic)
as there are more factors being considered in the design.

 But then the question is, Does this depend? /Interaction?


 Interactions explained in two ways here. So, two different stories are
being told. But you should only do one, the inevitably more interesting
one.
 Interaction #1 displayed: If you are in an easy course, save you money.
IN TUTORIALS: You have to code your IVs. Your textbook explains this.
Univariate: 1 DV.

You might also like