Epi and Biostats

Question 1

What is epidimiology

Answer 1

Epidemiology is the study of distribution and determinants of health-related states or events in specified populations, and application of the study to the control of health problems

Question 2

Define confounder and describe two important characteristics of confounders

Answer 2

A confounder is a variable other than the main one you were studying (e.g. age) that is associated with both the exposure (e.g. activity level) and outcome (e.g. heart disease, distorting the true relationship between the exposure and the outcome.

A confounder must:

1. NOT be on the causal pathway and
2. be associated with the exposure and must also be a risk factor for, or affect the probability of recognizing, the outcome

Question 3

Describe six different ways to control for confounding

Answer 3

STUDY DESIGN
1. Randomization: selection method decides who is exposed and who is unexposed (e.g. random number generator)
2. Restriction: limit enrolment based on known confounders (e.g., do not include alcohol drinkers)
3. Matching: based on potential confounders (e.g., match cohort based on age)
ANALYSIS
4. Stratification: by a particular variable (e.g. age, sex)
5. Standardization: such as standardizing for age
6. Multivariant analysis: control for multiple confounders using regression models.

Question 4

Explain and provide an example of a mediating factor

Answer 4

A mediating factor is an intermediate process between the exposure and the outcome.

An example would be hypertension, which is an intermediate process between obesity and heart disease.

Another example for hypertension is that hypertension is an intermediate process between salt intake, and stroke.

Question 5

Define effect modification and describe the two different categories of effective modification.

Answer 5

Effect modification is a real relationship between the exposure and the outcome and a third variable modifies the direction or magnitude of that effect.

Synergistic: positive interaction

Antagonistic: negative interaction

Question 6

Explain stratification

Answer 6

Stratification is a method used to determine whether or not the relationship between an exposure, and an outcome is due to a confounder or impacted by an effect modifier.

The exposure and outcome is stratified by the potential confounder/effect modifier. If the relationship is not due to the confounder, then the incidence of the outcome will be higher in the exposed, than in the unexposed in every stratum, and the strength of the association (stratum-specific OR or RR) will be similar in every stratum. In the case of confounding, the crude RR or OR will be different from the adjusted OR or RR.

If the relationship is impacted by an effect modifier, then the strength of the association (stratum-specific OR or RR) will be different in every stratum.

Question 7

Explain causation

Answer 7

causation is the relationship between cause and effect.

Question 8

Describe the general conditions under which causation can be explained.

Answer 8

Necessary cause mean that without the cause, the effect cannot occur, however, sometimes the cars can occur without the effect. For example, example, a pathogen, causing a disease.

Sufficient cause means the effect must always occur when the cause is present. For example, decapitation causing death.

Causation can be described as necessary and sufficient (X -> Y); necessary, but not sufficient (X+Z->Y); sufficient, but not necessary (X->Y, Z->Y), or neither sufficient nor necessary (X+Z->Y, Z+K->Y).

Question 9

Describe the different types of relationship associations between cause-and-effect.

Answer 9

1. Causal: real association where change an exposure produces change an outcome.
2. Not causal: real association where change in exposure, does not necessarily result in a change in the outcome. (association may be due to confounding factor).
3. Spiritus: false association due to various causes of bias or simply due to chance.