George Washington University PubH 6003: Principles and Practice of Epidemiology Week 8 Quiz 1)In a hospital-based case-control study of the relationship between x-rays and thyroid cancer, 50 cases admitted for thyroid cancer and 100 controls admitted during the same time period for treatment of hernias were studied

George Washington University

PubH 6003: Principles and Practice of Epidemiology Week 8 Quiz

1)In a hospital-based case-control study of the relationship between x-rays and thyroid cancer, 50 cases admitted for thyroid cancer and 100 controls admitted during the same time period for treatment of hernias were studied. Only the cases were interviewed and 20 of them were found to have been exposed to x-rays in the past based on the interviews and medical records. The controls were not interviewed, but a review of their hospital records when they were admitted for hernia surgery revealed that only 2 controls had been exposed to x-ray therapy in the past. Based on this information, what source of bias is least likely to be present?

A.            Recall bias

B.            Bias due to controls being nonrepresentative of the non-diseased population

C.            Bias due to use of different methods of ascertaining exposure in cases and controls

D.            Bias due to loss to follow-up from the control group

E.            Selection bias for exposures to x-ray therapy in the past.

2.            Which of the following is true about the p-value?

A.            Indicates the probability of seeing the observed result, and results more extreme, by chance alone (given that the null hypothesis is true)

B.            Indicates the probability that the null hypothesis is true

C.            Rules out the role of bias and/or confounding

D.            Indicates that the results observed are of medical or public health significance

3.            Information bias occurs

A.            After the subjects have entered the study

B.            Before the subjects have entered the study

C.            Both of the above

D.            None of the above

4.                            An analytic method that simultaneously adjusts for the effects of several variables (confounders) is called:

A.            Multivariate

B.            Stratification

C.            Matching

D.            Restriction

5.            Which of the following statements is true about a 95% confidence interval?

A.            Considering an interval that excludes the null value as significant is equivalent to considering a p-value of less than 0.05 to be significant.

B.            The range within which the true measure of effect lies with a stated probability, or a certain degree of assurance (95% in this instance)

C.            The confidence interval is calculated around the point estimate, and quantifies the variability around the point estimate for 95% of all estimates given a certain sample size

D.            All of the above

6.            It has been suggested that women diagnosed with cervical cancer more accurately report their past use of estrogens than women without cervical cancer. This is an example of:

A.            Selection bias

B.            Surveillance bias

C.            Interviewer bias D.                          Recall bias

E.            Non-response bias

7.            Non-differential misclassification tends to bias study results in which direction from the null hypothesis (Ho:)?

A.            Towards the null hypothesis

B.            Away from the null hypothesis

C.            Either towards or away from the null hypothesis

8.            Interviewer/recording bias can occur in:

A.            Case-control studies only

B.            Cohort studies only

C.            Experimental studies only

D.            Any type of epidemiologic study

9.            Selection bias is most likely to occur in studies where:

A.            Only exposure has occurred at the time of subject selection

B.            Only outcome has occurred at the time of subject selection

C.            Exposure and outcome have already occurred at the time of subject selection

10.          A method used in study design to control for confounding that involves the selection of study subjects so that potential confounders are distributed identically across the study groups is called:

A.            Multivariate modeling

B.            Stratification C. Matching

D.            Restriction