EPIB 301 Final Exam Questions with Verified
Correct Answers
incidence
= the rate of new (or newly diagnosed) cases of the disease
= generally reported as the # of new cases occurring within a period of time (per month or per
year)
Example- twenty people were recently diagnosed with the flu
prevalence
= actual number of cases alive with the disease either during a period of time or at a particular
date in time
= duration X incidence
-the only way to not be included in prevalence is to be cured or to die
= decreased by out-migration cases
Example- proportion of persons who reported having arthritis as part of the 2013 National
Health Interview Survey
Example 2- proportion of 3-6 year olds with asthma in the US
relative risk
= generic term used to represent all of the classes of relative measures of association
-Used interchangeably with risk ratio (cumulative incidence ratio) b/c it's the most commonly
used relative measure of association
= use for prospective or retrospective cohort studies
Example Interpretation- Smokers have 7.5 TIMES THE RISK of developing bladder cancer relative
to individuals who do not smoke
risk difference
= difference in cumulative incidence
RD = 0 = no association
,RD < 0 = exposure associated with decreased risk of disease
RD > 0 = exposure associated with increased risk of disease
Example Interpretation- Subjects with recent flu vaccinations had 98 fewer deaths per 10,000
subjects over the following year compared to subjects without recent flu vaccinations
odds ratio
measure of the association between frequency of exposure and frequency of outcome used in
case-control studies
-use for case-control or retrospective cohort studies
Example Interpretation- Compared to individuals who do not vape, individuals who vape have
2.8 times the odds of getting a lung disease
random error
= error due to chance
systematic error
= error due to recognizable source, leads to incorrect estimate of association
confounding
= "mixing of effects"
-Estimate of the effect of exposure on disease is distorted because it is mixed with the effect of
other factors associated with exposure and the disease
-Can control for in the design and analysis stages of a study:
Example = Design: randomization, restriction, matching
Example = Analysis: restriction, stratified analysis, statistical modeling
· Must be:
-Associated with the exposure
-Associated with the outcome
-Not an intermediate step on the causal pathway
effect modification
-phenomenon that the investigator needs to describe their study results rather than eliminate in
the design or analysis stage
, -Occurs when stratum-specific estimates are meaningful different from one another
-True exposure-disease association is biologically different for two strata ("heterogeneity of
effect")
-Should be described, not adjusted/controlled for
ethics
Belmont Report = cornerstone statement of ethical principles
-established the basic code of ethical research (respect for person, beneficence, and justice)
ecological
= investigator actively manipulates which groups receive agent under study
+
-may provide information about the context of health
-can be performed if individual level measurements are not available
-can be conducted rapidly and with minimal resources
-good for early stage of knowledge
-
-ecologic fallacy (conclusions based on aggregate data may not extend to individuals)
-imprecise measurement of exposure
case control
= clearly define two groups at the start: one with the outcome/disease and one without the
outcome/disease. They look back to assess whether there is a statistically significant difference
in the rates of exposure to a defined risk factor between the groups
General steps- decide of definition of disease, select cases, select controls, ascertain exposure
status
-CANNOT BE USED TO EXAMINE MULTIPLE OUTCOMES
+
-useful with rare outcomes
-quick and easy to complete
-inexpensive
-smaller number of subjects
-
-exposure measurement can be inaccurate
Correct Answers
incidence
= the rate of new (or newly diagnosed) cases of the disease
= generally reported as the # of new cases occurring within a period of time (per month or per
year)
Example- twenty people were recently diagnosed with the flu
prevalence
= actual number of cases alive with the disease either during a period of time or at a particular
date in time
= duration X incidence
-the only way to not be included in prevalence is to be cured or to die
= decreased by out-migration cases
Example- proportion of persons who reported having arthritis as part of the 2013 National
Health Interview Survey
Example 2- proportion of 3-6 year olds with asthma in the US
relative risk
= generic term used to represent all of the classes of relative measures of association
-Used interchangeably with risk ratio (cumulative incidence ratio) b/c it's the most commonly
used relative measure of association
= use for prospective or retrospective cohort studies
Example Interpretation- Smokers have 7.5 TIMES THE RISK of developing bladder cancer relative
to individuals who do not smoke
risk difference
= difference in cumulative incidence
RD = 0 = no association
,RD < 0 = exposure associated with decreased risk of disease
RD > 0 = exposure associated with increased risk of disease
Example Interpretation- Subjects with recent flu vaccinations had 98 fewer deaths per 10,000
subjects over the following year compared to subjects without recent flu vaccinations
odds ratio
measure of the association between frequency of exposure and frequency of outcome used in
case-control studies
-use for case-control or retrospective cohort studies
Example Interpretation- Compared to individuals who do not vape, individuals who vape have
2.8 times the odds of getting a lung disease
random error
= error due to chance
systematic error
= error due to recognizable source, leads to incorrect estimate of association
confounding
= "mixing of effects"
-Estimate of the effect of exposure on disease is distorted because it is mixed with the effect of
other factors associated with exposure and the disease
-Can control for in the design and analysis stages of a study:
Example = Design: randomization, restriction, matching
Example = Analysis: restriction, stratified analysis, statistical modeling
· Must be:
-Associated with the exposure
-Associated with the outcome
-Not an intermediate step on the causal pathway
effect modification
-phenomenon that the investigator needs to describe their study results rather than eliminate in
the design or analysis stage
, -Occurs when stratum-specific estimates are meaningful different from one another
-True exposure-disease association is biologically different for two strata ("heterogeneity of
effect")
-Should be described, not adjusted/controlled for
ethics
Belmont Report = cornerstone statement of ethical principles
-established the basic code of ethical research (respect for person, beneficence, and justice)
ecological
= investigator actively manipulates which groups receive agent under study
+
-may provide information about the context of health
-can be performed if individual level measurements are not available
-can be conducted rapidly and with minimal resources
-good for early stage of knowledge
-
-ecologic fallacy (conclusions based on aggregate data may not extend to individuals)
-imprecise measurement of exposure
case control
= clearly define two groups at the start: one with the outcome/disease and one without the
outcome/disease. They look back to assess whether there is a statistically significant difference
in the rates of exposure to a defined risk factor between the groups
General steps- decide of definition of disease, select cases, select controls, ascertain exposure
status
-CANNOT BE USED TO EXAMINE MULTIPLE OUTCOMES
+
-useful with rare outcomes
-quick and easy to complete
-inexpensive
-smaller number of subjects
-
-exposure measurement can be inaccurate
