Measuring association and making causal inference

Question 1

What is the epidemiologic approach?

Answer 1

Is there an association between a factor and the disease?

If yes, is it a causal relationship?

Question 2

What are two ways to quantify the strength of an association (for a binary outcome)?

Answer 2

1. difference

2. ratio

Question 3

What is a binary outcome?

Answer 3

dependent variable we are looking at in a model
ill/well
case/control
alive/dead

Question 4

If you had to translate the incidence ratio into words what would you say based on this example:
Tx 1 cumulative incidence = 0.5
Tx 2 cumulative incidence = 0.3
incidence ratio = (0.5/0.3) = 1.7

Answer 4

Treatment one increases the cumulative incidence of remission by 1.7 fold comparing to treatment 2

Question 5

What type of difference measurements can be used for measures of association - binary outcomes?

Answer 5

Risk difference (proportion)
Rate difference

Question 6

What type of ratio measurements can be used for measures of association - binary outcomes?

Answer 6

Risk ratio (proportion)
Rate ratio
Odds ratio

Question 7

What range do proportions, risks, cumulative incidence have to be in? Rates?

Answer 7

Risk = 0-1
Rate = > 0

Question 8

What does a difference of 0 imply?

Answer 8

no association

Question 9

What do difference measures range from?

Answer 9

• infinity to + infinity

Question 10

What do ratio measures range from?

Answer 10

0 to infinity

Question 11

What does a ratio of 1 imply? > 1? < 1?

Answer 11

1 – No association
> 1 – exposure is positively associated with disease
< 1 – exposure is negatively associated with disease

Question 12

By looking at ratio, how will you decide which has the strongest association?

Answer 12

ratio further away from 1

Question 13

How do you calculate a risk ratio?

Answer 13

risk proportion 1 / risk proportion 2

Question 14

How do you calculate risk rate?

Answer 14

diseased / population at time

Question 15

How do you find the risk?

Answer 15

diseased / population at risk

Question 16

Define odds

Answer 16

the ratio of the probability an event will occur to the probability it will not occur

Question 17

Is odds itself proportion, ratio, or probability?

Answer 17

ratio

Question 18

What can odds range to if we calculate it?

Answer 18

0- infinity

Question 19

What will the odds ratio tell us in words?

Answer 19

based on the conditions you are looking at factor x with increase the outcome odds by ___ fold compared to factor y

Question 20

Calculate the odds.

Answer 20

of dz animals/ # of non dz animals

Question 21

When thinking about causal association what 4 things could the association be due to?

Answer 21

Bias
Confounding
Chance
Cause

Question 22

What are the three main types of bias?

Answer 22

1. Selection
2. Information
3. Specification

Question 23

T/F

Bias might be reduced or controlled in study design

Answer 23

True

Question 24

What else do we call bias?

Answer 24

systematic error

Question 25

What do you look at when deciding if something was associated by chance?

Answer 25

statistical significance.

Question 26

What is a selection bias?

Answer 26

The group used for a study is not a good representative of the population. They have been selected to fit certain criteria.

Question 27

What is an information bias?

Answer 27

The information in the study was inaccurately collected. The question was worded wrong, the recipient may have knowingly acted one way

Question 28

What is a specification bias?

Answer 28

Using a wrong statistical model that may make assumptions. It may make the wrong assumption

Question 29

What is confounding?

Answer 29

a lack of comparability between study groups resulting in a bias in the estimation of the effect of interest.

Question 30

What must a confounder be?

Answer 30

1. cause of the outcome, independent the exposure 2. correlated with exposure in the study population 3. Not part of the causal pathway

Question 31

T/F | A confounder is affected by exposure or outcome

Answer 31

False

Question 32

What is chance also called?

Answer 32

random error

Question 33

What is a valid result?

Answer 33

This is an unbiased one. We are measuring exactly what we want to measure

Question 34

What is a precise result?

Answer 34

Has small variability | Use confidence interval to look at precision

Question 35

What are 4 major threats to a study's validity?

Answer 35

selection bias information bias specification bias confounding

Question 36

What are 3 factors that may affect precision of a study?

Answer 36

``` Random variation (error) Sample size Study design (efficiency) ```

Question 37

What are Hill's guidelines for causal inference?

Answer 37

1. strength of association 2. consistency 3. specificity 4. temporality (cause must occur first) 5. biological gradient (dose-response) 6. plausibility 7. analogy

Question 38

What do Hill's guidelines for causal inference help us do?

Answer 38

Helps us decide if a situation is more likely to be causal or not

Question 39

What is more likely to be causal, strong or weak association?

Answer 39

strong, however, a weak association can still be causal

Question 40

Why can't we rule out causal association if there is poor consistency?

Answer 40

some effects are produced by their causes only under unusual circumstances.

Question 41

What does specificity suggest? Is this a good recommendation to assess causal relationship?

Answer 41

requires that a cause leads to a single effect, not multiple. Not a good recommendation -- most causes can lead to different effects

Question 42

What is a must for causal relationship according to Hill's guidelines?

Answer 42

Temporality | refers to the necessity that the cause precedes the effect in time

Question 43

What is the analogy part of Hill's guidelines?

Answer 43

Similar results can be found elsewhere

Question 44

T/F | One cause leads to one disease

Answer 44

False Diseases have a multifactorial etiology -- various factors interact to result in disease Disease is an ecological problem

Question 45

What are the A-B-Cs?

Answer 45

``` Is the observed Association due to: Bias Confounding Chance Cause ```