Effect modification. Flashcards
When does Effect Modification occur?
When the strength of association varies over different categories of a third variable in an association study.
Name four examples of effect modifiers?
- Sex.
- Age.
- Environmental exposure.
- Genetic effect.
Do you modify for effect modification?
No. It is not an error.
What OR’s do you look at when looking at effect modification?
Stratum specific OR’s.
How do you evaluate stratum specific OR’s?
- Calculate P values on homogeneity tests.
2. Evaluate overlap of CI’s on stratum specific OR’s.
What homogeneity test do you use to calculate the p values for effect modification?
Breslow-day test.
What is the conceptual definition of an effect modifier?
The effect of the exposure and potential modifier differ from the expected joint effect.
What is synergism?
Effect modifier extenuates the effect of an exposure.
Antagonism?
Effect modifier diminishes/eliminates the effect of the exposure.
For something to be an effect modifier what must the OR be after stratifying?
Statistically different.
When will an effect modifier be described as being in the ‘grey zone’ what is overlapping?
The confidence intervals.
Apart from using the Mantel-Haenzsel OR what other way can you adjust for confounding?
Report confounders separately.
What is the equation for the null hypothesis for the Mantel-Haenzsel test?
H0= OR1=OR2
What is the alternative hypothesis for the Mantel-Haenzsel test?
H1= OR1 is not equal to OR2.
What distribution is used in the Mantel-Haenzsel test?
Chi squared to 1 dof.
In words what is the null hypothesis for the Mantel-Haenzsel test?
Stratum specific OR’s are homogenous.
What is not considered in the Breslow-Day test?
Ordering in the strata.
Why is it difficult to stratify by multiple variables in the Breslow-Day test?
Data becomes sparse.
Can you control for additional covariates in the Breslow-day test?
No.
What is the equation for Q?
Sumk (weightk x log (logORk- LogORW )^1/2
What is the equation for LogORw (weight log odds ratio).
sum( logORk x weightk) / sum weightk
What is the reference category in the multiplicative model when determining if something is an effect modifier?
No exposure/ No effect.
What are you determining in the multiplicative model?
Marginal association of effect/ exposure on outcome to see if there is a multiplicative interaction between the effect modifier and the exposure.
What is H0 in the multiplicative model?
OR++= OR-+ x OR+-
I=1.
What is the equation for the interaction effect in the multiplicative model?
OR++/(OR+- x OR-+) = 1
If I>1 what type of interaction is present?
Synergism.
If I<1 what type of interaction is present?
Antagonism.
What type of studies do additive models measure the effect of an effect modifier in?
Prospective studies.
What is the null hypothesis for an additive model on a cohort study?
RD++ = RD+- + RD-+
What is the null hypothesis for an additive model on a case-control study?
OR++ = OR-+ + OR+-
Why is it difficult to assess additive effects in a case control study?
- Disease risk (incidence) is not available as there is no time point.
- Can not directly test with a logistic regression model (as this is a multiplicative model).
What sort of regression models are used to look at additive effects?
Linear, Poisson.
What sort of regression models are used to look at multiplicative effects?
Logistic, poisson, survival (COX) analysis.
What does the side of an interaction effect influence?
The size of the sample needed to detect its effect.
What is another name for effect modification?
Biological modification.
What needs to be present for an effect modification to be properly assessed?
- A clear biological mechanism.
2. All available data.
What does a statistical modification imply?
That a modification has been observed in a few studies but there is no sufficient supporting evidence.
Interactions can be seen to occur when they do not actually exist. Why? (3 things).
- Chance.
- Systematic error.
- Varying exposure doses between strata.
When does qualitative effect modification occur instead of quantitative? What does this mean?
When measures of effect in different strata have different directions. This means that effect modification occurs on both the multiplicative and additive scale.
If effect modification occurs on both scales you will always observe this in a single study. True or false?
False.
Explain the phenomenon of reciprocity in terms of effect modifier Z, exposure E and outcome D.
If Z modifies the effect of E on D than Z also modifies the effect of E on D.
Does the following statement describe an effect modifier or a confounder?
Belongs to a specific study.
Confounder.
Does the following statement describe an effect modifier or a confounder?
Exists in nature.
Effect Modifier.
Does the following statement describe an effect modifier or a confounder?
Different effects in different strata.
Effect modifier.
Does the following statement describe an effect modifier or a confounder?
Increases biological knowledge of mechanism.
Effect modifier.
Does the following statement describe an effect modifier or a confounder?
Prevented in the design stage, controlled for in analysis stage.
Confounder.
Does the following statement describe an effect modifier or a confounder?
Creates confusion in the data.
Confounder.
Does the following statement describe an effect modifier or a confounder?
Allows targeting of public health outcome.
Effect modifier.
