A.R.M Revision Flashcards

(63 cards)

1
Q

How is the variance related to the standard deviation?

A

The standard deviation is equal to the square root of the variance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Power analysis is an attempt to…

A

Adress Type II errors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

An effect size of d = 0.73 is…

A

A medium effect

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are the four core principles of the Singapore statement on research integrity?

A

Honesty, Accountability, Professionalism, and Stewardship

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

In inferential statistics, error is…

A

Variance not accounted for by the model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Cronbach’s Alpha values should be between what values to be considered reliable?

A

0.7 and 0.9

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is not a theory led type of regression analysis?

A

Stepwise Methods

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Regarding the assumptions of multiple regression, what do we mean by ‘non-zero variance’?

A

Predictor variables should not have a variance (standard deviation) greater than zero

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

I, a researcher, wanted to conduct a multiple regression with four predictors, where they were aiming for a large effect, what would be the minimum sample size required?

A

39

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What does the Durbin-Watson test, test for?

A

For independent errors

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What results tells us whether an individual predictor is significantly associated with the outcome variable?

A

The t-test results

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

In a hierarchical regression, what variables are typically entered in step 2 of the analysis?

A

More exploratory or new variables where the relationship with the outcome variable is not established

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What types of variables would need to be dummy coded before being entered into a regression analysis?

A

Categorical or ordinal variables (with 3+ categories)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

To meet the assumptions of homoscedasticity, the residuals at each level of the predictor variables should have…

A

The same variance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What does the change in F statistic tell us?

A

Whether the new additional variables significantly increase the proportion of variance accounted for

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

If you want to compare the strength of associations between different predictor variables and the outcomes variable, what statistic would you read?

A

The standardised beta

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What post-hoc test is used with a two-way ANOVA design?

A

Bonferroni

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What do post-hoc tell us

A

Whether there are significant differences between conditions in an individual variable, when the variable includes 3+ conditions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What post-hoc is used with a between-subjects design?

A

Tukey

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

When should you read and interpret the Mauchly’s test of sphericity table

A

If the within-subjects variable has three or more conditions

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

Regarding the non-parametric equivalent of two-way ANOVAs, what statistical test should be used to analyse a between-subjects variable with three or more conditions?

A

Kruskal-Wallis

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

Regarding the non-parametric equivalent of two-way ANOVAs, what statistical test should be used to analyse a within-subjects variable with three or more conditions?

A

Friedman

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

Regarding the non-parametric equivalent of two-way ANOVAs, what statistical test should be used to analyse a between-subjects variable with two conditions?

A

Mann-Whitney U

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Regarding the non-parametric equivalent of two-way ANOVAs, what statistical test should be used to analyse a within-subjects variable with two conditions

A

Wilcoxon

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Covariate variables must be
Continuous
26
Running an ANCOVA allows researchers to...
Reduce error variance
27
When testing the independence of the covariate and the IV in an ANOVA you want the result to be...
Non-significant
28
ANCOVA controls for covariation...
Statistically
29
Which test should be used for checking the assumptions of homogeneity of covariance matrices?
Box's test of equality of covariance matrices
30
What does the assumption of homogeneity of covariance matrices mean in MANOVA?
The correlation between any two dependent variables is the same in all groups
31
Pillai-Bartlett trace is similar to...
the ratio of SSm/SSt (Known as R2)
32
When entering predictors into a moderation analysis, they should first be...
Centred
33
What are Baron and Kenny's four conditions of mediation?
1. X -> Y 2. X -> M 3. M -> Y 4. The direct effect of X on Y must be reduced or eliminated when M is included in the model
34
What does ANOVA stand for?
Analysis of Variance
35
In a two-way ANOVA what F value tells us the effect on the DV of both IVs?
The interaction
36
Can you violate the assumptions of homogeneity of variance?
Yes, but only with equal group numbers
37
Can you violate the normal distribution assumption?
Yes, but the distributions must follow the same direction
38
If the result of Mauchly's test of sphericity is significant, you need to read across which line of the tests of within-subjects effects table?
The Greenhouse-Geisser line
39
What does HARKing stand for?
Hypothesising After Results are Know
40
Is between-subjects regression a type of multiple regression?
No
41
In terms of regression analyses what does VIF stand for?
Variance Inflation Factor
42
In regression analyses, what statistic tells us whether the model is significant?
The F value
43
In regression analyses, what statistic tells us the value of Y when X = 0?
The intercept
44
What two statistics tell us the measure of the slope?
Standardised beta and unstandardised beta
45
What visual on a graph is most often an indicator of an interaction effect?
The lines crossing
46
In regression if we have high multicollinearity, what does that mean?
Our predictors are too highly correlated
47
What is one ANOVA where Mauchly's test of sphericity will not be produced?
Two-way between subjects Mauchly's test of sphericity is only done on within-subjects with 3+ levels
48
In what kind of analysis is the change in R2 statistic used?
Hierarchical regression
49
What symbol is used to represent the relationship between a predictor and a mediator?
a
50
What value of Cronbach's alpha is typically used to indicate good internal reliability?
0.70 Not 0.80 because that would be considered excellent
51
To test whether a relationship between predictor and outcome is due to a third variable, you use...
Mediation
52
What kind of analysis tests for the difference across conditions (the IV) when controlling for scores on a continious variable (the covariate)?
ANCOVA
53
In moderation, what does a significant interaction mean?
The effect of the IV depends on the level of the moderator
54
A team of researchers were interested in the long-term impact of natural disasters on sleep quality. They recruited a sample of participants in the weeks following an earthquake which hit the country they were living in. They grouped the participants based on the distance they lived from the epicentre of the earthquake; a ‘near’ group who were living within 40km of the epicentre and a ‘far’ group who were living over 40km away from the epicentre. All participants were asked to complete the Pittsburgh Sleep Quality Index (PSQI; Buysse et al., 1989) three times; within a few weeks of the earthquake, again two years later and again four years later. Scores on the PSQI range from 0 (good sleep) to 21 (poor sleep). What type of ANOVA should be used to analyse data from the above study?
A 2X3 mixed ANOVA
55
H1: Motivation to learn will positively predict end of year exam marks. H2: Behavioural difficulties will negatively predict end of year exam marks. H3: Being a non-native-English speaker will negatively predict end of year exam marks. Are these hypotheses one-tailed or two-tailed?
All three hypotheses are one-tailed
56
The researcher decided to conduct a follow-up study to see if the relationship between motivation to learn and exam marks was stronger amongst children who were raised by parents with higher socio-economic status (as measured by the household income) compared to parents with lower socio-economic status. What would be the most suitable test to use?
Moderation
57
What does it mean if the result of a Kolmogorov-Smirnov test is non-significant?
Data is not normally distributed
58
What does it mean if the result of a Levene’s test is non-significant?
There is homogeneity of variance across conditions
59
What does it mean if the result of a Mauchly's test of sphericity is non-significant?
Then sphericity is assumed and you should read the sphericity assumed line of the results table
60
If a minimum sample size of 39 is required to see a large effect, according to Cronbach's Alpha. What is the minimum sample size for a medium effect?
85
61
If a minimum sample size of 39 is required to see a large effect, according to Cronbach's Alpha. What is the minimum sample size for a small effect?
602
62
When checking multicollinearity, what does the VIF value indicate?
If VIF is greater than 10 there is a problem If VIF the average VIF is above 5 then regression may be biased
62
When checking for issues with