Module 13

Question 1

Definition of confounding bias

Answer 1

A situation in which the effects of two processes are not separated. The distortion of the apparent effect of an exposure on the dz is brought about by the association of the exposure with other variable(s) that can influence the outcome

Question 2

3 criteria of confounders

Answer 2

1. Be a risk factor (or protective factor) for the dz
2. Be associated with the exposure, independently of the dz
3. Not be an intermediate step in the causal pathway between exposure and dz (or not be the result of the exposure)

Question 3

What does a confounder do?

Answer 3

Confuses our conclusions about the relationship between an exposure and an outcome
It distorts the odds ratio or relative risk

Question 4

Role of confounding

Answer 4

Should always be considered as a possible explanation for an observed association, particularly in observational studies.
Confounding may over or underestimate a true association
Unlike selection and information bias, one may prevent confounding at the design stage or control for confounding at the analysis stage of a study.

Question 5

What are the three methods of controlling confounding in the design of the study?

Answer 5

1. Restriction (all study designs)
2. Randomization (clinical trials)
3. Matching (case-control studies and exposure-based cohort studies)

Question 6

More details on restriction

Answer 6

May prohibit variation of the confounder in the study groups.
-For example, restricting participants to a narrow age category can eliminate age as a cofounder
Provides complete control of known confounders
Cannot control for unknown confounders
Can be done in any study designs

Question 7

Disadvantages of restriction

Answer 7

This limits generalizability (external validity) but often improves feasibility and focus
Impractical to restrict on a large number of factors

Question 8

More details about randomization and confounding

Answer 8

Random assignment makes intervention and control groups look as similar as possible
Chance is the only factor that determines group assignment
Controls for both known and unknown cofounders
Guarantees that tx assignment is not based on pt prognostic factors
Works best with large samples

Question 9

More details about matching and confounding

Answer 9

A strategy for controlling at both the design and analysis levels of a study
Commonly used in case-control and exposure-based cohort studies
Matches participants in the comparison and study groups according to the value of the suspected or known confounding variable to ensure equal distributions
Controls only known confounders (the variables on which participants were matched)

Question 10

Why is matching done?

Answer 10

So that the control (or unexposed participant) has identical (or at least, very similar) values of the confounding variable as the case (or exposed participant)

Question 11

What are common matching variables?

Answer 11

Age and sex

Question 12

What are the two types of matching?

Answer 12

Individual
Frequency

Question 13

Individual matching

Answer 13

The pairing of one or more controls to each individual case (or one or more unexposed individuals to each exposed participant) based on similarity in sex, race, or other variables

Question 14

Frequency matching

Answer 14

The proportion or percentage of cases and controls (or exposed and not exposed) with particular characteristics is matched

Question 15

Advantages of matching

Answer 15

There is direct control of potential confounders, on which you matched
Fewer participants are required than in unmatched studies of the same hypothesis

Question 16

Disadvantages of matching

Answer 16

1. Data collection is more complex.
   -Costly because extensive searching and recordkeeping are required to find matches
   Data analysis must take account of the matching
   -Different methods of analysis must be done
   The effect (on dz) of the matching variable cannot be estimated
   Matching cannot be removed. You cannot unmatch later.
   One can “overmatch”

Question 17

What is overmatching?

Answer 17

Matching on a variable that is associated with the exposure or outcome but not both
-Not a true confounder
-The confidence interval is widened
Matching on a variable that is in the causal pathway between exposure and outcome
-Not a true confounder (It is a mediator or intervening variable, instead of a confounder)
-Biases the odds ratio or relative risk
Matching on too many variables
-Too many confounders
-Cost and time to find suitable participants meeting all the matching criteria

Question 18

What are the two analysis strategies to control confounding (after all the data is in)

Answer 18

Stratified analysis or stratification
Multivariate modeling or multivariate techniques

Question 19

What is the result of collecting data on potential confounding variables at the beginning of the study

Answer 19

It makes it possible to adjust for these potential confounders at the analysis level through stratification and multiple regression techniques.

Question 20

Definition of stratified analysis or stratification

Answer 20

Analyses performed to evaluate the effect of an exposure on an outcome within homogenous categories or strata (levels) of the confounder

Question 21

When is there positive confounding?

Answer 21

If the crude is stronger than the stratified

Question 22

When is there negative confounding?

Answer 22

If the crude is weaker than the stratified

Question 23

When is there no confounding?

Answer 23

If the crude = the stratified

Question 24

10% rule

Answer 24

Used when comparing adjusted back to the crude number.
Add and subtract 10% of the odds ratio back to the odds ratio or relative risk of the crude number
-i.e., 10% of 1.63 = 0.163
-1.63 + 0.163 = 1.47
-1.63 - 0.163 = 1.79
-Set the lower and upper as boundaries
If the adjusted (i.e, stratified) ORs or RRs are less than the lower boundary or greater than the upper boundary, then it’s not due to random error
Means it could be a confounder.

Question 25

Advantages of stratification

Answer 25

Performing analyses within strata is a direct and logical strategy
The computational procedure is straightforward
Minimum statistical assumptions must be satisfied for the analysis to be appropriate

Question 26

Disadvantages of stratification

Answer 26

Small numbers of observations of some strata
A variety of ways to form strata with continuous variables (like age)
Categorization produces loss of information
Difficulty in interpretation when several confounding factors must be evaluated

Question 27

Multivariate modeling

Answer 27

Use computers to construct mathematical models that describe simultaneously the influence of exposure and other independent variables that may be confounding the association between exposure and outcome

Question 28

Sometimes the confounding is only _______ or can _______

Answer 28

Partial, go in the opposite direction

Question 29

What is used to control for several potential confounders at once?

Answer 29

Logistic regression

Question 30

What does logistic regression do?

Answer 30

It provides odds ratios adjusted for the potential confounders in the model

Question 31

Where is logistic regression used?

Answer 31

Cohort studies
Case-control studies
Cross-sectional studies

Question 32

When is cox proportional hazard regression used?

Answer 32

When adjusting for several potential confounders at once in a cohort study (or clinical trial). It generates “hazard ratios”

Question 33

Hazard ratios = ?

Answer 33

Relative risks when several confounders are adjusted for in a multivariate analysis

Question 34

Advantages of multivariate analysis

Answer 34

Continuous variables do not need to be converted to categorical variables
Allows for simultaneous control of several exposure and confounding (or independent) variables in a single analysis

Question 35

Disadvantages of multivariate analysis

Answer 35

Potential for misuse, as more statistical assumptions have to be satisfied than in stratified analysis