# 2-way ANOVA & Beyond Flashcards Preview

## PS3021 Stats > 2-way ANOVA & Beyond > Flashcards

Flashcards in 2-way ANOVA & Beyond Deck (29)
1
Q

What 4 things are required for establishing causality?

A

Theoretical credibility, co-variation, elimination of confounds and temporal precedence.

2
Q

Describe necessary causation.

A

If you see Effect(B), you must be at level B.

3
Q

Describe sufficient causation.

A

If you see Effect(B), you may be at level B.

4
Q

A

Where a correlation seems to go one direction, but adding a factor means there are many correlations, possibly in a different direction.

5
Q

What is observed in 2-way ANOVA?

A

Grand mean + F1 effect + F2 effect + Interaction effect + error.

6
Q

What does adding a factor that matters do?

A

Decrease SS, df and error term.

7
Q

What does adding a factor that doesn’t matter do?

A

No decrease in SS, decrease in df, increase in error term and power, possible loss of significance.

8
Q

What is used to control for multiple t tests?

A

The overall effect size given by R squared.

9
Q

What is eta-squared?

A

The proportion of all variability explained the effects/interactions.

10
Q

What is partial eta-squared?

A

The proportion f the variance that could be explained, that the effect/interaction explains.

11
Q

What does including participants as a random factor allow us to do?

A

Account for variability in a dataset due to individual differences.

12
Q

Why do we calculate the average across participant means rather than the average across trials?

A

We usually want to talk about ”people on average” rather than the average trial.

13
Q

What makes up a nesting effect?

A

The mean for one level of nested factor 2 - (grand mean + one level of factor 1 effect).

14
Q

What is observed in a nested ANOVA?

A

Grand mean + F1 effect + F2(F1) effect + error.

15
Q

How can bivariate data be analysed?

A

Pearson’s correlation and simple linear regression/1-way ANOVA.

16
Q

How can multivariate data be analysed?

A

Partial and multiple correlation and multiple linear regression/n-way ANOVA/ANCOVA.

17
Q

A

The partial variance of X3.

18
Q

A

The total variance of X3.

19
Q

Give 2 key aspects of partial correlation.

A

It is a “pure” measure uncontaminated by other variables and its uniqueness of variance makes it theoretically simpler.

20
Q

Give 2 key aspects of semi-partial correlation.

A

It has a more intuitive baselines and it allows easy comparison of coefficients because X3 is constant.

21
Q

How can ANCOVA be used to control for a variable?

A

You can add an extra variable, and use a regression line to estimate when X is the same.

22
Q

What is observed in an ANCOVA?

A

Grand mean + factor effect + participant effect + individual differences + noise.

23
Q

How can a covariant remove unwanted variability?

A

If some DV variability is attributed to the covariate it is removed from the error sum of squares.

24
Q

When can adding a covariate increase degrees of freedom?

A

When the covariate is not related to the DV.

25
Q

When can adding a covariate reduce power?

A

When it is co-linear with the first.

26
Q

What assumptions does ANCOVA share with ANOVA?

A

Normality of error distributions, homogeneity of error variance and independence of “error term.”

27
Q

What assumptions does ANCOVA share with regression?

A

Interval/ratio scale data and linear relationship.

28
Q

Give 3 reasons to use ANCOVA compared to ANOVA.

A

Accounts for more variability, “controls for” other variables and quantifies which subject characteristics are important.

29
Q

Give 3 things a good covariate should be.

A

Related to the dependent variable, unrelated to the other independent variables and unrelated to the other covariates.