Lecture 9 Flashcards

1
Q

A Scattergram plots each participants score on the

A

Independent variable against the dependent variable

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

In a Scattergram the dependent variable goes on which axis?

A

Y

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

There are 3 types of relationships found in scattergrams

A

Linear
Curvilinear
None

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

Correlation and linear regression can only be used for this type of Scattergram relationship

A

Linear or straight line relationship

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

Pearson correlation will only tell you if you have a ……type of relationship

A

Linear

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

If you have no linear relationship looking at a Scattergram what can’t you do?

A

Pearsons correlation

Linear regression

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

What’s the next step afte funding a linear relationship in your Scattergram?

A

You superimpose a line of best fit also called the regression line

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

Regression line best represents the

A

Relationship between the 2 varables

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

Regression line tells you if

A

Y can be predicted on X

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

Independent variable always goes on which axis?

A

X

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

Where can the effect size be found in a Scattergram in SPSS??

A

Top right corner where it says R2 linear = ……

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

Effect size is the….

A

Correlation of the two variables squared

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

In a Scattergram you’re looking for a line of best fit that is….

A

On an angle

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

If line of best fit is on an angle it means….

A

There is a relationship!!!

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

What does the Scattergram look like if there is no relationship??

A

Flatline/horizontal

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

Relationship is not strong when points are

A

Scattered all around Scattergram

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

5 points to think about with a Scattergram…

A
Type of relationship
Direction
Cluster
Gaps
Outliers
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

The easiest way to work out if two variables are related is by plotting them on a

A

Scattergram

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

What does direction of relationship refer to on a Scattergram?

A

Positive or negative

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

Type of relationship in a Scattergram refers to

A

Linear etc?

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

A line that goes up towards the right on a Scattergram is what type of relationship?

A

Positive - as one variable increases so does the other…

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

If the line goes up to the left of the Scattergram the relationship between variables is

A

Negative - as one variable increases the other decreases

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

Y stands for which variable?

A

Dependent

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

X is what variable?

A

Independent

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
Q

Gaps in the data suggest the existence of

A

Sub samples in the data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
26
Q

An R2 of 0 or similar on a Scattergram means that there

A

Is no linear relationship between the varables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
27
Q

What is covariance?

A

How two variables vary together

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
28
Q

If we want to see if there is a relationship between 2 variables we are actually interested in whether

A

Changes in one variable are met with changes in another variable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
29
Q

In covariance…When one variable deviates from it’s mean we would expect

A

The other variable to deviate from it’s mean in a similar way

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
30
Q

To calculate the exact similarity between the pattern of differences in covariance we calculate the…

A

Cross-product deviations

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
31
Q

When calculating variance essentially what you’re looking at is how

A

Each score deviates from it’s mean

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
32
Q

To get an average of the combined differences for the two variables you need to:

A

Sum the cross products

Divide by the number of cases minus 1

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
33
Q

Covariance formula:

A

CPF = (X - M2) (Y - M2)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
34
Q

Covariance mean of two different variables formula:

A

CovXY = Sum of [(X - Mx) (Y - My)] / N -1

35
Q

Degrees of freedom (N -1) give you

A

An unbiased estimate

36
Q

Covariance problem is that it depends on

A

The scales of measurement you’re using - it’s not a standardised measure

37
Q

Need to convert covariance into a set of standard set units to be able to

A

Compare it

38
Q

Covariance is converted to standard units by computing the

A

Pearsons r

39
Q

Pearsons r is most common in measuring

A

Association between two variables

40
Q

What type of scale do you need at least to use pearsons r?

A

Interval scale

41
Q

Interval scale means

A

Equal differences (1-2-3-4-5) with no true 0

42
Q

Ordinal scale is

A

Rank order - has no 0. Goes from smallest - biggest

43
Q

Nominal data is

A

Grouping data, data in categories. Numbers mean group names etc

44
Q

Pearsons r is the

A

Standardised covariance between two variables

45
Q

Pearson r formulae is

A

r = covXY / SxSy

46
Q

Pearsons r will only tell you about what sort of relationship?

A

Linear!!!

47
Q

Pearsons r can range from

A

-1 (strong neg) to +1 (strong pos)

48
Q

What is a weak pearsons r (correlation only!!)

A

0-0.29

49
Q

A moderate pearsons r is (correlation only!!)

A

0.30-0.59

50
Q

A strong pearsons r is (correlation only!!)

A

0.60-1.00

51
Q

Pearsons r does not reveal

A

Causality

52
Q

Pearsons r sig (effect size)

A

At .05

53
Q

Usually R2 converted to a

A

%

54
Q

Weak effect size

A
r = .10
R2 = .01
55
Q

Medium effect size

A
r = .3
R2 = .09
56
Q

Strong effect

A
r = .5
R2 = .25
57
Q

3 factors that influence the size of Pearson correlation

A

Sample size
Restriction of range or variability
Use of heterogeneous sub samples

58
Q

There are 2 mathematical assumptions for pearsons r

A

Interval scale data

Normality

59
Q

What is particularly bad for correlation and regression?

A

Outliers!

60
Q

A partial correlation is where there is

A

Overlapping variance - or how much variance is commonly shared by all variables

61
Q

A partial correlation will Allow you examine the relationship between

A

2 variables when the 3 has been removed

62
Q

Two types of partial correlation

A

Semi partial

Partial

63
Q

Semi partial correlation will only remove the effect of the 3rd variable

A

Only from the independent variable

64
Q

Partial correlation will remove the effect of the 3rd variable from

A

Both other variables

65
Q

Partial correlations give us a more

A

Accurate reflection of the relationship between two variables

66
Q

Partial correlations also tell us what variables

A

Shouldn’t go in the model together

67
Q

Why is partial correlation important?

A

We want to account for as much variance as possible!

68
Q

Doing a partial correlation helps you work out if you have

A

Multicollinearity between your variables

69
Q

Multicollinearity is where the overlap

A

Between variances is considerable

70
Q

You know if you have multicollinearity with 2 things

A

Pearsons r correlations exceed absolute value if .6

Or .8 with Field

71
Q

What correlation techniques do you use if your variables aren’t interval scale but categorical?

A

Chi squared
Phi
Cramer’s V
Cohens kappa

72
Q

What correlation techniques do you use if your variables aren’t interval scale but ranked or ordinal data?

A

Spearman rank

Kendalls W

73
Q

What correlation techniques do you use if your variables aren’t interval scale but categorical and interval data

A

Eta

Point biserial

74
Q

Is chi square non parametric or parametric?

A

Non-parametric

75
Q

Chi squares used in 2 situations…

A

To compare groups on one nominal/categorical variable

To determine if there is a relationship between 2 variables that are both nominal/categorical

76
Q

Pearson called the chi square test a

A

Goodness of fit

77
Q

Chi square called goodness of fit because it determines if there is a good fit between

A
The data (observed frequencies)
What would be expected from theory (expected freq)
78
Q

df - in a 2x2 table, df would =

A

(2 - 1) (2 - 1) = 1*1 = 1

79
Q

Chi square can be used when nominal/categoric variables have been measured on how many levels?

A

2 or more

80
Q

Chi square does not indicate

A

Strength OR relationship between variables

81
Q

Phi used for a

A

2x2 contingency tables

82
Q

2 methods to determine effect size in chi square analysis

A
Cramers v (most common)
Odds ratio
83
Q

Cramers v measure of effect size for weak, mod, strong are

A

.1
.3
.5

84
Q

Chi square has 2 mathematical assumptions:

A

Independence of observations (diff ppl in each of your groups and only tested once)
Expected cell frequencies must exceed 5