Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

Research Skills > Week 8 + 9 + 10 > Flashcards

Week 8 + 9 + 10 Flashcards

1
Q

What is ANOVA?

A

A parametric test - test for differences
Used when more than 2 groups and/or more than one IV
Allows to investigate the effect of multiple factors on your DV at the same time
Tries to determine whether we have a true effect of the IV

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

Why use ANOVA instead of several t tests?

A

Would have to carry out multiple separate tests
Every time conduct a t test there is a 5% probability of falsely rejecting the null hypothesis
Multiple tests increase risk of type 1 error

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

Is ANOVA or t tests more efficient?

A

With two groups - t test

With more than two groups - ANOVA

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

What are the assumptions for ANOVA?

A

DV consists of data at interval or ratio level
Population normally distributed
There is homogeneity of variance
For independent group designs, independent random samples must have been taken from each population

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

How does ANOVA work?

A

Analyses the different sources from which variations in scores arise
Looks at variability between and within conditions
Tries to determine whether we have a true effect of the IV (variance between conditions greater than within)

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

What does ANOVA stand for?

A

Analysis of variance

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

What is the relationship between the mean and variation?

A

The greater the difference in means, the greater the degree of variation between the conditions

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

What three sources does between group variance arise from?

A

Individual differences
Treatment effects
Random errors

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

What are treatment effects?

A

Effects of the IV(s) - what we are actually trying to measure
We want a difference between experimental conditions

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

What are individual differences?

A

People naturally vary but don’t want high individual differences as may falsely lead us to believe the IV is having an effect

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

What are random errors?

A

Errors can arise from:

  • varying external conditions e.g. differences in time of day of testing
  • state of the participant e.g. current focus of attention/motivation
  • experimenter ability to measure accurately
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is within group variance?

A

Variation between people within the same group
Can be called error variance
Not produce by the experimenter
Can arise form individual difference and random error

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

What is the logic of ANOVA?

A

Subjects in different groups should have different scores because they have been treated differently but subjects within the same group should have the same scores

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

What is partioning the variance?

A

The comparison of variance due to nuisance factors compared to variance due to our experimental manipulation

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

What is the F ratio?

A

F = between group variance / within group variance

Also

F = variance due to manipulation of IV / error variance

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

What does an F ratio of less than 1 indicate?

A

The effect of the IV is not significant

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

What will the F ratio be if error variance is small?

A

F will be greater than 1 and vice versa

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

How do we find out if the F ratio is significant?

A

SPSS will report the exact p level for a given F ratio

P value needs to be greater than or equal to 0.05 for the F value to be recognised as significant

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

What is a factor? (ANOVA)

A

The IV(s)

20
Q

What is a mixed ANOVA design?

A

When a study design includes one or more within subject factors and one or more between subject factors

21
Q

How to describe ANOVA designs

A

Need to specify

1) how many factors are involved in the design
2) how many levels there are in each factor
3) whether the factors are within or between subjects

22
Q

When do we use correlation analysis?

A

When we want to find out if there is a relationship between two variables

When we also want to find out the strength/direction of the relationship

23
Q

When is a bivariate correlation appropriate?

A

For exploring an association between two variables, where neither is categorical
E.g. height, weight, world ranking

24
Q

What are scatter plots used for?

A

To plot trends

25
Q

What is a correlation coefficient?

A

Ranges -1 to +1
Size indicates strength
Size indicates direction

26
Q

What are the suggested thresholds for interpreting the size of a coefficient?

A

0.8-1 very strong
0.6-0.79 strong
0.4-0.59 moderate
0.2-0.39 weak
0-0.19 very weak

27
Q

On a scatter plot, what axis does the IV go on?

A

The X axis

28
Q

What is the difference between Pearson’s r and Spearman’s rho?

A

Pearson’s r is the parametric correlation coefficient and Spearman’s rho is the nonparametric equivalent

29
Q

What are the parametric assumptions for correlation?

A 
Both variables must be ratio/interval 
Linear association (scatterplot) 
Association must show homoscedasticty (data points evenly distributed along regression lines)
30
Q

When do we check for homoscedasticty?

A

With independent samples t test we check for homogeneity of variance
Regression line minimises the sum of the residuals (distance of individual data points to line)

31
Q

What sample size should be used for Pearson’s r?

A

n>100

32
Q

What is the risk for smaller sample sizes?

A

That one or two extreme data points ‘drive’ the association

33
Q

What does Pearson’s r show?

A

The degree of linear relationship between the two variables measured on interval or ratio scales
r2 is the coefficient of determination - it tells how much of the variability of the DV is explained by the IV

34
Q

What is the difference between a two tailed and a one tailed significant test?

A

With a two tailed test we would reject H0 (no association) if wearing a positive or negative association

With a one tailed test we would only reject H0 if the association is in the direction that we expected

If it is, we halve the p value in the output

35
Q

When would you use Spearman’s rho?

A

Used where one or both variables are ordinal
Also where both variables are ratio/interval but the parametric assumptions have been breached
Calculates the ranked scores for each variable and considers the association between the ranks
Only appropriate when n is greater than or equal to 20
Association does not need to be linear but it must be monotonic (I.e. not change direction)

36
Q

What is Kendall’s tail test?

A

Non parametric test (similar to Spearman’s rho)
Should be used when data are normally distributed (but still ratio or ordinal)
Useful with small sets of data (<20)
Can deal with large numbers of tied ranks in the data

37
Q

Compare regression and correlation

A

Both investigate association between two ratio/interval variables
Both should have a sample size of minimum 100
Random sample
Regression specifies DV and IV, Pearson’s doesn’t
Pearson’s describes association between X and Y, regressions predicts value of Y (DV) from value of X (IV)

38
Q

What are residuals?

A

An observable estimate of the unobservable statistical error

The difference between the predicted value of Y and the actual value of Y

39
Q

What is meant by H0?

A

The slope is zero; there is no linear relationship between the variables

40
Q

What is meant by Ha?

A

The slope is not zero: there is a linear relationship between variables

41
Q

What are the assumptions for simple linear regression?

A

Both variables must be ratio/interval
The association must be linear
No univariate outliers

42
Q

What is the simple linear regression equation?

A

Y = a + bx
Y is the DV
a is the constant or intercept (the value of Y when x is equal to zero)
b is the coefficient or the slope of the line associated with this IV
x is the IV or predictor

43
Q

What is the regression equation?

A

Y = a + b(x)
Y is predicted value of Y
b(x) is specified value of x
a is the value of Y when x=0 (the intercept)

44
Q

What does E2 tell us?

A

To move the decimal point 2 places to the right

45
Q

What does standardised coefficients (beta) predict?

A

Specifics the predicted effect on Y if X increases by 1 SD

Research Skills (9 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions