Chapter 7: Bivariate Correlational Research Flashcards

1
Q

What are bivariate associations? Variable(s) are they measured or manipulated?

A

research involving two variables and they are measured not manipulated…because it would be hard to manipulate them

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

What is an association claim?

A

describes the relationship found between two measured variables. They can be positive, curvilinear, negative or zero.

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

To investigate associations researchers need to measure what?

A
  • the first and second variable in the SAME group
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Correlational studies that investigate more than two variables can or cannot be considered bivariate?

A

can be…they can examine the relationship between two variables at a time….

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

What are the ways associations between two variables can be described? (2)

A
  • scatterplots and the correlation coefficient r
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Categorical variable?

A

values fall in either one category or another

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

How are correlational data described when both variables are quantitative?

A

scatterplot

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

When one variable in the study is categorical what kind of graph will researchers use?

A
  • bar grap

L> shows the avg of each category

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

What do bar graphs allow us to examine ?

A
  • allow us to examine the difference between the average scores to sees whether there is a difference.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

When a difference is noted on bar graph for when one of the two variables is categorical what does this mean?

A
  • that there is an association! ….
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What statistics can be used when at least one of the variables is categorical?(3)

A
  • sometimes r
  • t test
  • point-biserial correlation
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is a t test used for when at least one variable is categorical?

A
  • whether the difference between the means is statistically significant
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What is a point-biserial correlation used for when at least one variable is categorical?

A
  • correlational coefficient that is similar to r but it is especially intended for evaluating the association between one categorical variable and one quantitative variable.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What is the phi coefficient used for?

A
  • designed to evaluate the association between two categorical variables!
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Are association claims characterized by a particular statistic or graph?

A

NO

- its characterized by a study design in which BOTH of the VARIABLES are MEASURED

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

What are the two most important validities for interrogating an association claim?

A
  • construct validity

- statistical validity

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

Aside from the two most important validities used for interrogation of an association claim what others can be looked at?

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

Is internal validity relevant to association claims?

A

NO

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

Construct validity??

L>q’s?

A
  • ask about this for BOTH variables…….how well each were measured aka the operationalizations of the variables
    L> does it have good reliability? Is it measuring what it is suppose to?
    L> evidence for face validity( is the measure an appropriate operationalization of the conceptual variable) , concurrent validity (is the measure correlating with a simultaneously occurring outcome it should be related to) ,discriminant validity ( extent a measure does not associate with measures of a measure that is theoretically different and it should not be related to) and convergent validity( extent a measure is associated with otter measures that are theoretically similar in constructs).
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

Statistical validity???

l> what should you consider?

A

asking what factors might have affected the scatterplot, correlation coefficient (r), bar graph or difference score that led to your association claim
L> considering effect size and its statistical sig, outliers, is a zero relationship possibly curvilinear?

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

Effect size?

A

describes the strength of an association

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

What are cohen’s values for identifying effect sizes?

A
  1. 1 (or -0.1) = weak/small
  2. 3( or -0.3) = medium or moderate
  3. 5 (or -0.5) = large or stronge
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What does a strong effect size mean?

A
  • that we can make more accurate predictions of one variable from another
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

Effect sizes indicate how ___ the result is.

A

important

- aka when all else is qual a larger effect size is often considered more important than a small one

25
Q

Does a small effect size always mean its not important?

A

NO it depends on the context

26
Q

The correlation coefficient r not only establishes the direction and strength of the relationship but it also determines what?

A

if it is statistically sig

27
Q

Even though if there is a zero association between two variables in a population what can happen?

A
  • by chance a study can use a sample that an association does show up….the correlation would be just by chance !
28
Q

What does statistical significance help evaluate?

A
  • evaluate the probability that the study’s results came from a population in which the association is really zero.
29
Q

Statistical sig calks provide a probability estimate (p). The p value helps researchers evaluate?

A

the probability that the sample’s association came from a population in which the association is zero…

30
Q

When is something non significant?

A

if p(aka sig) is greater than 0.05

31
Q

Statistical significance is related to what?

A

effect size
L> the stronger the correlation aka larger the effect size the more likely the correlation will be sig. This is bc the larger the association the less likely it could have been sampled just by chance from a pop that has a zero association

32
Q

Stat sig does not only depend on effect size, it also depends one what?

A

sample size.
L> ex: a very small effect size will be sig in a large population but that small es would not be sig in a small population. A small sample is more easily affected by chance events than a large sample is

33
Q

How is stat sig presented in journals etc?

A

p<.01 …or *

34
Q

One asterisks indicates a p value ____ than 0.05 and two asterisks indicate a p value ___ than 0.01.

A

less

less

35
Q

Spurious means what?

A

sometimes when an association between two variables the apparent overall association can be this meaning that the overall relationship is attributable only to systematic mean differences on subgroups
L> when you consider the subgroups separately there is no association

36
Q

Do subgroups within a sample always change the original association?

A
  • no
37
Q

Outlier?

A

an extreme score….a single case or a few that stands out far away from the pack

38
Q

A single outlier can have a strong effect on what?

A

correlation coefficient r

39
Q

What does the location of the outlier matter?

A

its impact varies depending on the location
L> it can make a medium sized correlation appear stronger, or a tong correlation appear weaker that it really is depending on its location

40
Q

Outliers can have a large impact on the ___ or ____ of the correlation. In a bivariate correlation, outliers are mainly problematic when they involve what?

A

direction or strength

L> when they involve extreme scores n both of the variables

41
Q

Whats the best way to identify outliers?

A

examine a scatterplot

42
Q

Outliers matter most in what kind of samples?

A

small samples

43
Q

In some rare cases when a study states there is no relationship between two variables the relationship may actually be what?

A

curvilinear

44
Q

How do researchers test for a curvilinear relationship when they suspect one exists?

A

via quadratic model …by testing the correlation between on variable and the square of the other

45
Q

When one tests on a curvilinear relationship with the correlation coefficient r what results do they get?

A

r=-0.01

L> the straight line that best fits this kind of relationship is a flat horizontal line which has a slope of zero.

46
Q

We need to consider internal validity with association claims to guard against what?

A

guard against causal temptation…the powerful automatic tendency to make a causal inference from any association claims we read.

47
Q

Correlation is not?

A

causation

48
Q

The temporal precedence rule of causation is sometimes called?

A

directionality problem because we don’t know which variable came first

49
Q

The internal validity rule is often called?

A

third variable problem

L>when you can come up with an alt explanation for the association btwn two variables…that alt is the third variable

50
Q

For the third variable to be plausible it must?

A

correlate logically with both of the measured variables in the original association

51
Q

Before we can accept a correlational association to be causal after covariance has been established further research will be needed to do what?

A
  • establish temporal precedence and internal validity before we would accept this relationship to be causal
52
Q

External validity?

A

can the association generalize to other ppl places and times

53
Q

When examining external validity does sample size matter?

A

not so much

L> the way the sample was selected does however

54
Q

What kind of sampling must be used to generalize to the rest of the population?

A

random sampling

55
Q

If random sampling is not used should we automatically reject the association found?

A

NO

L> accept the results and leave external validity to another study

56
Q

Moderator?

A

when the relationship between two variables changes depending on the level of a third variable….this is that third variable

57
Q

In correlational research moderators can inform what?

A

external validity
L> when the association is moderated we know that the association may not generalize from one of these situations to the others

58
Q

When asking about moderators what is our goal?

A
  • ask whether the association between the two variables is different within the levels of some moderator…..aka asking about subgroups, the overall association between the two variables is the same within the two groups.