Week 9

Question 1

What is the difference between systematic error and random error?

Answer 1

Random error is due to chance such as statistical fluctuations in the measurement of data. Systematic error is a result from errors in the selection or measurement such as bias.

Question 2

What is the difference between internal validity and external validity?

Answer 2

Internal validity is the validity of inferences drawn as they pertain to the members of the source population. External validity or generalizability is the validity of the inferences as they pertain to people outside of the source population.

Question 3

When does selection bias occur in the natural history of the study?

Answer 3

After the choosing the population and before selecting the study participants.

Question 4

When does information bias occur in the natural history of a study?

Answer 4

During the data collection step.

Question 5

Give an example of information bias

Answer 5

misclassification of former smokers as non-smokers

Question 6

What is non-differential misclassification?

Answer 6

When the misclassification of exposure status, for instance, is equal in the diseased and non-diseased groups (ie, it does not differ by disease).

Question 7

How does non-differential misclassification, which is independent of disease status, affect the estimates in a study?

Answer 7

non-differential misclassification biases toward the null (no effect)

Question 8

Twenty percent of the nonusers with CHD were categorized as users. Everyone else was classified accurately according to the truth. Is this an example of misclassification of exposure or disease?

Answer 8

misclassification of exposure

Question 9

Twenty percent of the nonusers with CHD were categorized as users. Everyone else was classified accurately according to the Truth. What type of misclassification is this an example of?

Answer 9

Differential misclassification of exposure, because the misclassification of exposure status is dependent on disease status.

Question 10

How can differential misclassification affect the estimates of study?

Answer 10

Differential misclassification can bias either toward the null or away from the nul.

Question 11

To have internal validity, a study must successfully address selection bias, information bias, and confounding, but not

Answer 11

generalizability

Question 12

In an observation study, threats to external validity include

Answer 12

effect modification

Question 13

What is validity?

Answer 13

The degree to which the inferences drawn from a study are warranted when account is taken of: the study methods, the representativeness of the study sample, and the nature of the population from which it is drawn.

Question 14

What is internal validity?

Answer 14

the credibility with which statements can be made about whether the association between the exposure and disease found in your study is a true association; what you observe is not due to random error, confounding or bias

Question 15

What is external validity (generalizability)?

Answer 15

validity of the inferences as they pertain to other circumstances; ability to generalize the results from a given study to populations beyond the study subjects.

Question 16

What study design is limited in generalizability?

Answer 16

clinical design, experimental study design; however, the bigger the sample, the more it is generalizable

Question 17

What are some threats to internal validity?

Answer 17

chance (random error), confounding, bias

Question 18

What are some threats to external validity?

Answer 18

internal validity, choice of study population, effect modification

Question 19

Why is effect modification a threat to external validity?

Answer 19

if the exposure causes disease only in the presence or absence of some third variable, generalizability may be limited

Question 20

What is bias?

Answer 20

the result of a systematic error in the design or conduct of a study; observed study results will tend to be different from the true results; happens in nature, unlike confounding, relates to the process of how the study is conducted

Question 21

bias can lead to incorrect:

Answer 21

measures of disease occurrence or association, estimate of statistical significance

Question 22

what is selection bias?

Answer 22

individuals have different probabilities of being included (selected, recruited, retain) in the study sample according to relevant study characteristics (exposure/disease)

Question 23

What is information bias?

Answer 23

systematic tendency for individuals selected for inclusion in the study to be erroneously placed in different exposure/disease categories. (ex: misclassification)

Question 24

When can selection bias occur in cohort studies?

Answer 24

if the frequency of risk factors in the exposed group(s) is different than that in the comparison group; more commonly, differential losses to follow-up

Question 25

What is control selection bias in case control studies?

Answer 25

when the selection of controls in case-control study is associated with exposure status

Question 26

What is Berksonian Bias?

Answer 26

occurs when cases and controls are selected from a subpopulation instead of the general population; when both cases and controls are sampled from a hospital

Question 27

information bias examples

Answer 27

recall bias, measurement bias, misclassification, interviewer bias, observer bias, respondent bias

Question 28

how can we minimize information bias?

Answer 28

getting expert opinion, using validated instruments and objective measures, standardized protocols and training data collection team

Question 29

what is interviewer bias?

Answer 29

behavior of the interviewer may influence respondent answers

Question 30

In what study designs are exposure-related biases more likely to be present?

Answer 30

case-control (population based)

Question 31

what is observerr bias?

Answer 31

ascertainment of outcome is influenced by knowledge of exposure or outcome status

Question 32

In what study designs are outcome-related biases more likely to be present?

Answer 32

cohort

Question 33

what is non-differential misclassification of disease?

Answer 33

non-differential misclassification of disease; disease is misclassified proportionally among exposed and non-exposed

Question 34

what is non-differential misclassification of disease?

Answer 34

non-differential misclassification of disease; disease is misclassified proportionally among exposed and non-exposed

Question 35

What is non-differential misclassification of exposure?

Answer 35

exposure is misclassified proportionally among diseased and non-diseased

Question 36

How can one measure the ability to distinguish between who does and does not have a disease (validity/truth)?

Answer 36

sensitivity and specificity

Question 37

what is sensitivity?

Answer 37

the ability of a test to correctly identify those who have the characteristic of interest (a/a+c)

Question 38

what is specificity?

Answer 38

the ability of a test to correctly identify those who do not have the characteristic of interest. (d/d+b)

Question 39

what type of bias is lead time bias?

Answer 39

information bias

Question 40

what type of bias is length bias?

Answer 40

selection bias

Question 41

what is lead-time bias

Answer 41

overestimation of survival duration due to earlier detection due to earlier detection by screening than clinical presentation

Question 42

what is length bias?

Answer 42

occurs when some people who are screened have disease that progresses more slowly than all people who have the disease.

Question 43

what are examples of cross-sectional biases?

Answer 43

incidence-prevalence bias, temporal bias

Question 44

what is incidence-prevalence bias?

Answer 44

including prevalent cases in a study when the goal is to make inferences about incident cases

Question 45

what is temporal bias?

Answer 45

cannot establish temporal sequence between exposure and outcome

Question 46

observer bias and respondent bias are common in cohort designs. true or false?

Answer 46

true

Question 47

recall bias and interviewer bias are common in case-control designs. true or false?

Answer 47

true