Unit 02: Bias & Causation

Question 1

“any systematic error in the design, conduct or analysis of a study that results in a mistaken estimate of an exposure’s effect on the risk of disease” is the definition of:

Answer 1

Bias

Question 2

bias differs from random error because it is ____ in nature

Answer 2

systematic

Question 3

What kind of study compares a variable group and a control group?

Answer 3

case-control

Question 4

what type of study determines the rate of disease in each group if a case-control study identifies evidence of an assocciation?

Answer 4

cohort study

Question 5

a systematic difference between those participating in a study (or contributing data) and those who are not participating is an indication of ____ bias

Answer 5

selection

Question 6

if without a factor, a disease does not occur, does this make the factor necessary or sufficient?

Answer 6

necessary

Question 7

If with a factor, a disease always occurs, does this make the factor necessary or sufficient?

Answer 7

sufficient

Question 8

if a factor is believed to be the cause of a disease, exposure to the factor must occur before disease development indicates a ____ relationship

Answer 8

Temporal

Question 9

nonresponse bias is a form of ____ bias

Answer 9

selection

Question 10

When participants who withdraw from a longitudinal study are systematically different from those who remain this is ____ bias, a form of selection bias

Answer 10

loss to follow-up

Question 11

____ effect is a phenomenon that occurs when studying a population of actively employed individuals to assess some aspect of their health. Since a certain level of health is required to work, people who participate in such a study are often in better health than those who cannot participate. (form of selection bias)

Answer 11

healthy worker effect

Question 12

When the means for obtaining information about the subjects in the study are flawed so that some of the information gathered regarding exposures and/or disease outcomes is incorrect, ____ bias may occur

Answer 12

information

Question 13

assigning participants the wrong exposure and/or outcome status is termed as ____ bias, a form of information bias

Answer 13

misclassification

Question 14

when ____ misclassification bias occurs, all groups are equally likely to be accurately, or inaccurately, assessed or assigned to a particular exposure or outcome group.

Answer 14

non-differential

Question 15

when ____ misclassification bias occurs, one group of participants is more likely than another group to be inaccurately assigned to a particular exposure or outcome group.

Answer 15

differential

Question 16

____ bias occurs when a certain group is more likely to remember certain information and is a form of information bias

Answer 16

recall

Question 17

____ bias occurs when a participant may be reluctant to disclose particular information because of attitudes, beliefs, and perceptions and is a form of information bias

Answer 17

reporting

Question 18

In a study of whether exposure A is a cause of disease B we say that a third factor, factor X is ____ if the following are true:
- Factor X is a known risk factor for disease B.
- Factor X is associated with factor A, but is not a result of factor A.

Answer 18

confounding

Question 19

How can we address confounding at the design stage?

Answer 19

• Randomization: In certain studies, all potential CFVs can be distributed equally among groups. This way each group has the same level of a given CFV, and as a result, the effect of the CFV is equal on both sides.
• Restriction/Exclusion: When recruiting participants, researchers will restrict or exclude people on the basis of the presence of a given factor, or ensure that only one level of a CFV is present.
• Matching: match the cases to the controls for the factor that we suspect could be a possible confounder

Question 20

How can we address confounding at the analysis stage?

Answer 20

• Stratification: stratify the data using the confounding variable and then calculate disease prevalence in each stratum