Question 1

In a case-control study,a researcher found no association between exposure to A and disease B.Later she found out that there was a misclassification when measuring exposure to A,in both cases and controls.What is a potential explanation for the results (no association) of this case-control study?
A) Nondifferential misclassification
B) Differential misclassification
C) Selection bias
D) Confounding
E) Effect-modification

Accepted Answer

This is an example of nondifferential misclassification.The fact that the misclassification affected both cases and controls indicates a nondifferential misclassification,which dilutes the association between A and B.

Question 2

Investigators think that income might be a confounder in the relationship between Hispanic ethnicity and cardiovascular disease.They conduct a case-control study and they match cases and controls based on income.They find that Hispanics are more likely to have cardiovascular disease as compared with non-Hispanics.What would you conclude about income as a potential confounder in this association?
A) Income is a confounder.
B) Income is not a confounder.
C) Income is an effect modifier.
D) Income is not associated with cardiovascular disease.
E) Income is not associated with ethnicity.

Accepted Answer

In a case-control study,if,after matching for a potential confounder,we still find an association between the exposure and the outcome,we can say that the potential confounder is actually not a confounder.

Question 3

Epidemiologists tried to investigate the role of factor Z in the exposure-disease relationship.They developed three tables to show the exposure-disease relationship based on the status of factor Z.Based on the information given,what is the role of factor Z in the exposure-disease relationship?Overall
$\begin{array}{|l|l|l|} 
\hline
& \text { Case } & \text { Control } \
\hline \text { Exposed } & 1,050 & 500 \
\hline \text { Unexposed } & 300 & 700 \
\hline
\end{array}$

Factor X present
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 700 & 250 \
\hline \text { Unexposed } & 200 & 350 \
\hline
\end{array}$

Factor X absent
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 350 & 250 \
\hline \text { Unexposed } & 100 & 350 \
\hline
\end{array}$

A) Factor Z is a confounder.
B) Factor Z is an effect measure modifier.
C) Factor Z is a mediator.
D) Factor Z is an outcome.
E) Factor Z does not have any role in the exposure-disease relationship.

Accepted Answer

A

Question 4

Epidemiologists tried to investigate the role of factor Y in the exposure-disease relationship.They developed three tables to show the exposure-disease relationship based on the status of factor Y.In this analysis,what is the odds ratio in the overall population?$\text { Overall }$
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 1,000 & 500 \
\hline \text { Unexposed } & 200 & 500\
\hline
\end{array}$

$\text { Factor } Y \text { present }$
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 800 & 250 \
\hline \text { Unexposed } & 100 & 250 \
\hline
\end{array}$

$\text { Factor } Y \text { absent }$
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 200 & 250 \
\hline \text { Unexposed } & 100 & 250 \
\hline
\end{array}$

A) 0.5
B) 1.0
C) 2.0
D) 5.0
E) 8.0

Accepted Answer

The odds ratio (OR) is calculated as (Exposed Cases/Exposed Controls) / (Unexposed Cases/Unexposed Controls). For the overall population: OR = (1000/500) / (200/500) = 5.0.

Question 5

Investigators think that income might be a confounder in the relationship between Hispanic ethnicity and cardiovascular disease.They conduct a case-control study,and they match cases and controls based on income.They find that Hispanics are more likely to have cardiovascular disease as compared with non-Hispanics.What is the measure of association used in such study?
A) Risk ratio
B) Relative risk
C) Incidence rate ratio
D) Attack rate
E) Odds ratio

Accepted Answer

Odds ratio is the proper measure of association used in case-control study.

Question 6

Epidemiologists tried to investigate the role of factor Y in the exposure-disease relationship.They developed three tables to show the exposure-disease relationship based on the status of factor Y.Based on the information given,what is the role of factor Y in the exposure-disease relationship? Overall
$\begin{array}{|l|l|l} 
& \text { Case } & \text { Control } \
\hline \text { Exposed } & 1,000 & 500 \
\hline \text { Unexposed } & 200 & 500
\end{array}$
 Factor Y present
$\begin{array}{|l|l|l} 
& \text { Case } & \text { Control } \
\hline \text { Exposed } & 800 & 250 \
\hline \text { Unexposed } & 100 & 250
\end{array}$
 Factor Y absent
$\begin{array}{|l|l|l} 
& \text { Case } & \text { Control } \
\hline \text { Exposed } & 200 & 250 \
\hline \text { Unexposed } & 100 & 250
\end{array}$

A) Factor Y is a confounder.
B) Factor Y is an effect measure modifier.
C) Factor Y is a mediator.
D) Factor Y is an outcome.
E) Factor Y does not have any role in the exposure-disease relationship.

Accepted Answer

In the overall table,the odds ratio equals the odds of exposure among the cases (1,000/200) divided by the odds of exposure among the controls (500/500).The ratio in overall equals 5.In the table when Y is present,the odds ratio equals the odds of exposure among the cases (800/100) divided by the odds of exposure among the controls (250/250).This ratio in overall equals 8.In the table when Y is absent,the odds ratio equals the odds of exposure among the cases (200/100) divided by the odds of exposure among the controls (250/250).This ratio in overall equals 2.The odds ratios of exposure vary by the presence of factor Y,and the overall odds ratio is also different from stratified odds ratios.This association indicates that factor Y is an effect measure modifier which changes the effect of exposure to the outcome by its status.

Question 7

This table shows incidence rates (per 100,000) of groups exposed to neither risk factors or to one or two risk factors for lung cancer.What is the expected value of incidence rate X on asbestos exposure group among smokers in multiplicative scale? Incidence Rates of Lung Cancer by Asbestos and Smoking Exposure Status
$$\begin{array}{r}
\text { Smoking status  }\quad\
\text { Asbestos exposure }
\begin{array} {|l|l|l|} 
\hline& \text { Yes } \quad \quad& \text { No }\quad\quad \
\hline \text { Yes (regular exercise) } & 2.0 & 2.6 \
\hline \text { No (no exercise) } & 4.0 & x\
\hline
\end{array}\end{array}$$
A) 4.0
B) 6.0
C) 8.0
D) 12.0
E) 24.0

Accepted Answer

The expected value of incidence rate X on asbestos exposure group among smokers in multiplicative scale is 4.0 * 2.0 = 8.0.

Question 8

Epidemiologists tried to investigate the role of factor X in the exposure-disease relationship.They developed three tables to show the exposure-disease relationship based on the status of factor X.Based on the information given,what is the role of factor X in the exposure-disease relationship? $\text { Overall }$
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 1,000 & 500 \
\hline \text { Unexposed } & 200 & 500\
\hline
\end{array}$

$\text { Factor } Y \text { present }$
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 800 & 250 \
\hline \text { Unexposed } & 100 & 250 \
\hline
\end{array}$

$\text { Factor } Y \text { absent }$
$\begin{array}{|l|l|l|}
\hline & \text { Case } & \text { Control } \
\hline \text { Exposed } & 200 & 250 \
\hline \text { Unexposed } & 100 & 250 \
\hline
\end{array}$
A) Factor X is a confounder.
B) Factor X is an effect measure modifier.
C) Factor X is a mediator.
D) Factor X is an outcome.
E) Factor X does not have any role in the exposure-disease relationship.

Accepted Answer

The answer of Epidemiologists tried to investigate the role of...

Question 9

Smoking participants of a cohort study are more likely to drop out.It is known that the effect of asbestos on getting cancer is much stronger among smokers.When analyzing data for this study,researchers find no association between asbestos and cancer.A potential explanation for the results of the study is
A) confounding.
B) effect modification.
C) selection bias.
D) information bias.
E) specificity of association.

Accepted Answer

Because those participants who dropped the study were particular regarding the association (smokers),those who remained in the study showed a biased attenuated association.

Question 10

This table shows incidence rates (per 100,000) of groups exposed to neither risk factors or to one or two risk factors for lung cancer.What is the expected value of incidence rate X on asbestos exposure group among smokers in additive scale? Incidence Rates of Lung Cancer by Asbestos and Smoking Exposure Status
$$\begin{array}{r}
\text { Smoking status  }\quad\
\text { Asbestos exposure }
\begin{array} {|l|l|l|} 
\hline& \text { Yes } \quad \quad& \text { No }\quad\quad \
\hline \text { Yes (regular exercise) } & 2.0 & 2.6 \
\hline \text { No (no exercise) } & 4.0 & x\
\hline
\end{array}\end{array}$$
A) 4.0
B) 6.0
C) 8.0
D) 12.0
E) 24.0

Accepted Answer

The additive model suggests that the combined effect of two risk factors is the sum of their individual effects. Here, the incidence rate for smokers with no asbestos exposure is 2.6, and for non-smokers with asbestos exposure is 4.0. Therefore, the expected incidence rate for smokers with asbestos exposure is 2.6 + 4.0 - 2.0 = 8.0.

Quiz 15: More on Causal Inference: Bias, Confounding, and Interaction

In a case-control study,a researcher found no association between exposure to A and disease B.Later she found out that there was a misclassification when measuring exposure to A,in both cases and controls.What is a potential explanation for the results (no association) of this case-control study?