Psychological research skills

Question 1

One way analysis of variance has what kind of a design?

Answer 1

One IV with three of more levels (conditions) or 2 or more IVs

Question 2

Assumptions for one way ANOVA are

Answer 2

normally distributed data
homogeneity of variance
independence of observations
Interval or ratio data

Question 3

if parametric assumptions for One way ANOVA are not met, you should use the corrected factors?

Answer 3

Between subjects, Kruskal-Wallis

Within subjects, Friedman

Question 4

Which test is used to check for normality?

Answer 4

Shapiro-Wilk, Kolmogorov-Smirnof has too few observations most of the time.

Question 5

Which test is used to check for equality of variances?

Answer 5

Levene’s.

Question 6

Description in the ANOVA needs to include?

Answer 6

Decribe the statistical test, the variables, the purpose of the statistical analysis.

Question 7

In APA format presenting the means?

Answer 7

a sentence for 3 or fewer, a table for 4-20 and 20+ is a graph.

Question 8

There is an extra assumption in the within-participants ANOVA, which is? And it is tested with?

Answer 8

Sphericity. Mauchly’s test of Sphericity, only for factors with three or more levels.

Question 9

When writing up Shapiro-Wilk versus when wiriting up Levene’s?

Answer 9

W(value) vs F(df1,df2)= …

Question 10

Partial Eta Squared is? And it’s values indicate?

Answer 10

Measure of practical importance, 0.01 small effect, 0.06 medium effect, 0.14 large effect.

Question 11

In a two-way between participants ANOVA there needs to be

Answer 11

Two or more IVs with one or more levels.

Question 12

There is an interaction when…

Answer 12

The scores of a condition differ across factors.

Question 13

What is a typer 1 error?

Answer 13

Rejecting the null hypothesis when it is in fact true. alfa is significance.

Question 14

What is a type 2 error?

Answer 14

Failing to reject null hypothesis when it is false. B is significance.

Question 15

Disadvantages to within-subjects design are… and can be fixed?

Answer 15

practice-effects and carry over effects. Fixed by complete counterbalancing.

Question 16

In writing up a significant sphericity…

Answer 16

The Chi Square statistic for Maulchy’s test is significant, indicating that teh assumption of sphericity is not met for the effect of - X2(juu)….

Question 17

Whixh corrector factor to use for violates sphericity assumption?

Answer 17

Greenhouse Geisser when epsilon <0.75, Huyn-Feldt if >0.75

Question 18

What does power depend on?

Answer 18

Type 1 error
Typer 2 error
Sample size
Statisctical method used
Experimental design
effect-size

Question 19

How to increase power?

Answer 19

by reducing overlap between two distributions, aim to create low variablitiy = LOW ERROR

1. increasing sample size, minimises sampling error
2. eliminating poor methodology or poor tevhonolgy, minimises experimental error
3. within-part design, no individual differences error

Question 20

Partial Eta Squared and effect size,

Answer 20

Partial Eta Squared is the proportion of variance that is due to the effect

Question 21

If data non normal…

Answer 21

Can remove outliers, or transform e.g. logarithmic transfromarion, Arcsine…

Question 22

Sphericity violation indicates an

Answer 22

Increased chance of type 2 error and decreased power.

Question 23

When violations of aaumptions are problematic?

Answer 23

small samples
data-samples are non-normal in different ways
one variance is more than 4 times the other
unequal sample size in each condition

Question 24

If interactions are found, need to follow up with…

Answer 24

Test for simple main effects

Question 25

ANCOVA assumptions

Answer 25

the covariate and the experimental (IV) should be independent from eachother and should not share variance
matching/randomisation is important

Question 26

How to check ANCOVA assumption?

Answer 26

run a t-test/ANOVA with the covariate as DV and condition remaining the IV, anova should be non-significant.

Question 27

Positivism?

Answer 27

Talk provides - reliable data on thoughts, a route to cognitions
Procedure; standardised questions, structured schedule
neutral interviewer (distant?)
Not interested in interviewer’s contribution: only transcribe/record interviewee’s answers.
Variability in response

Question 28

Emotionalism

Answer 28

Experience as focus, need to get to interviewee’s real feelings
‘deep’, unstructured interview to get beyond
presentation of self, need intimacy, empathy
interviewer self-disclosure encouraged
Not interested in interviewer’s contribution: only transcribe/record interviewee’s answers

Question 29

constructionism

Answer 29

Interested in how people construct versions of world
People do things with words (different to positivist approach)
Analyse constructions: what functions do they serve?
how are they are ‘worked up’ to appear neutral descriptions of events?