L20: Measures of Association Flashcards

1
Q

What are the measures of association?

A
  • relative risk (risk ratio and rate ratio)

- odds ratio

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

How do we construct a contingency table to present the data?

A

Exposure yes no as row and outcome yes no as column

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

How to express RR and OR in words?

A

Those who were exposed have x time the risk/odds of developing the outcome compared to those unexposed.

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

When is risk ratio used?

A

Used in cohort study when all subjects are followed for the same duration of time

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

How to calculate cumulative incidence?

A

a/a+b ; c/c+d

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

How to calculate risk ratio?

A

cumulative incidence in exposed group / cumulative incidence in unexposed group

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

When is rate ratio used?

A

Used in cohort study when subjects have diff lengths of follow up.

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

How to calculate incidence rate?

A

a/total person time (exposed)

c/total person time (unexposed)

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

How to calculate rate ratio?

A

incidence rate in exposed group / incidence rate in unexposed group

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

When is odd ratio used?

A

Typically used in case control study.

In case control study, relative risk cannot be calculated directly. Subjects identified based on outcome status -> cannot calculate incidence

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

How to calculate odds ratio?

A

cross product = ad/bc

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

When is odds ratio a good estimate of risk ratio?

A

When the outcome is rare (<10%) –> use case control study

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

What do we do if there are multiple exposure groups?

A

Select the least exposed group as the reference group

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

What does the confidence interval of RR or OR tell us?

A
  • statistical significance of the association

- precision of the point estimate (RR or OR)

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

How to tell statistical significance of RR or OR?

A

If CI does not include 1 –> statistical significant association
If CI includes 1 –> association not statistically significant

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

What does a wide CI tell you?

A

Imprecise result. Results should be interpreted with caution regardless of statistical significance.