USMLE® STEP 1 QUESTION
BANK LATEST 2025 -
COMPLETE QUESTIONS AND
ANSWERS.
Your All-in-One Practice Tool
USMLE Step 1 Biostatistics
__ exposure and outcome are measured simultaneously at a particular point of time (snapshot study).
-
(Correct ANS)Cross-section study
- prevalence study
- exposure and outcomes measured simultaneously
- surveys
__ is the tendency of the study population to affect the outcome since they are aware that they are
being studied. -
(Correct ANS)Hawthorne effect
__ or external validity pertains to the applicability of study results to other populations (the results of
a study in middle-aged woman would not be expected to be applicable to elderly men). -
(Correct ANS)Generalizability
___ bias occurs when the investigator's decision is adversely affected by knowledge of the exposure
status. -
(Correct ANS)Observer bias
___ can be applied to both disease pathogenesis and exposure to risk modifiers. Exposure to risk
factors and the initial steps in disease pathogenesis sometimes occur years before clinical
manifestations are evident. -
(Correct ANS)Latency period
___ design studies involve randomization to different interventions with additional study of 2 or more
variables. -
(Correct ANS)Factorial design
ex: study design that has 3 different drug interventions (metoprolol, ramipril, amlodipine) and 2
different variable BP endpoints
,___ is design is best for determine the incidence of a disease. Comparing the incidence of the disease
in 2 populations (with and without a given risk factor) allows for the calculation of relative risk. -
(Correct ANS)Cohort
___ is said to be successful when a similarity of baseline characteristics of the patients in the
treatment and placebo group is seen. -
(Correct ANS)Randomization
___ is statistical method that is commonly employed to compare the means of 2 groups of subjects. -
(Correct ANS)two-sample t test
___ is the measure of random error. The tighter the confidence interval, the more ___ the results. -
(Correct ANS)Precision
- increasing the sample size increases precision
___ is used to compare proportions. A 2x2 table may be used to compare the observed values with
the expected values. -
(Correct ANS)Chi-square test
___ when an external variable positively or negatively impacts the effect of a risk factor on the
disease of interest. -
(Correct ANS)Effect modification
A ___ test gives similar result on repeat measurements. -
(Correct ANS)Reliable test
- reliability is maximal when random error is minimal
ARR = -
(Correct ANS)a/a+b - c/c+d or (RR - 1)/RR
bias from errors of measurement -
(Correct ANS)information bias
bias from inaccurate recall of past exposure by subjects -
(Correct ANS)recall bias
bias from loss to follow up in prospective studies -
(Correct ANS)attrition bias aka selection bias
-achieve high rates of follow up to reduce potential for attrition bias
-other types of selection biases from innappropriate selection or poor retention of subjects:
ascertainment/sampling bias, nonresponse bias, berkson bias, prevalence bias
bias from patients exaggerating behavior, not admitting to something embarassing, claiming to take
meds when actually missing doses -
(Correct ANS)unacceptability bias
bias from the manner of selecting subjects for a study or from selective losses during follow up -
(Correct ANS)selection bias
bias from time differentials ie cancer screening prolongs survivial but actually just detecting earlier,
not improving treatment -
(Correct ANS)lead time bias
bias when people do not respond to phone calls or return surveys -
(Correct ANS)nonresponse bias; can cause error if nonresponders differ from responders; try to
contact nonresponders repeatedly, or list nonresponders as unknown in data analysis, never make up
responses
,bias when study sample is not representative of the target population with respect to exposure and
outcome -
(Correct ANS)sample distortion bias
bias when subjects affect their outcome since they know they are being studied -
(Correct ANS)hawthorne effect
tendency of study population to affect outcome because they are aware they are being studied and
change their behavior
bias where investigator is not blinded; decision is affected by knowledge of exposure status -
(Correct ANS)observer bias
-investigator decision adversely affected by knowledge of exposure status ie knowing the race of
patients in a study between ethnicity and ESRD ties disease reports more frequently to black patients
bias where outcome is obtained from a patients subjective and not by objective diagnostic methods -
(Correct ANS)respondent bias
Biostats 2x2 table -
(Correct ANS)
Calculate attributable risk percent (ARP). -
(Correct ANS)Excess risk in population that can be explained by exposure to particular risk factor
ARP = (RR - 1)/RR
Calculate risk. -
(Correct ANS)Divide the number of disease subjects by the total number of subjects (all the people at
risk)
Risk = probability of getting a disease over a certain period of time
calculating attributable risk -
(Correct ANS)AR = excess risk in a population that can be explained by exposure to a particular risk
factor; calculate by subtracting baseline risk in an unexposed population from the risk in an exposed
population, then divide result by risk in exposed
AR = risk in exposed - risk in unexposed / risk in exposed
*AR = (RR-1)/RR*
calculating negative predictive value -
(Correct ANS)people with a negative test who actually do not have the disease
NPV = true negatives / true negatives + false negatives
*NPV = D / D+C*
calculating positive predictive value -
(Correct ANS)people with a positive test who actually have the disease
PPV = true positives / true positives + false positives
*PPV = A / A+B*
calculating relative risk -
(Correct ANS)RR = a/(a+b) / c/(c+d)
case control vs retrospective cohort -
(Correct ANS)the order in which outcomes and risk factors are assessed
case control: find outcome first, then look for associated factors
retrospective: find risk factors first, then find outcome
, Common types of systemic error in statistical studies -
(Correct ANS)
confounding is defined as -
(Correct ANS)mixing up the effect of exposure with the effect of an extranous factor (confounder)
-extraneous factor must have some properties linking it with the exposure and outcome of interest
-must have properties linking it with the exposure and outcome
Correlation coefficient -1.0 and +1.0 -
(Correct ANS)r = + means increase one variable means increase in other
r = - means increase in one means decrease in the other
r = 0 means no correlation
correlation coefficient (r) meaning -
(Correct ANS)strength and direction of a linear association between 2 variables; - means changing in
opposite directions, + means positive correlation in the same direction
null = 0, no correlation
the closer r is to 1 or -1 the stronger the correlation
Different study designs -
(Correct ANS)
Distribution curves sensitive and specificity compare TN and TP. -
(Correct ANS)
effect modification -
(Correct ANS)an external variable affects the effect of a risk factor on the disease of interest
-distinguish it from confounding by performing a stratified analysis centered on the variable of
interest
-effect modification is not a bias but a natural phenomenon
effect of prevalence on PPV and NPV -
(Correct ANS)higher prevalence = higher PPV
lower prevalence = higher NPV
exposure odds ratio measurea association in __ studies where exposure of people with disease (cases)
is compared to those without disease (controls) -
(Correct ANS)case control
False negative ratio = ___. -
(Correct ANS)= 1 - sensitivity
False positive ratio = ___. -
(Correct ANS)= 1 - specificity
hazard ratio -
(Correct ANS)ratio of an event rate occuring in the treatment group compared to the non-treatment
group
<1 indicates treatment group has a lower event rate
>1 indicates treatment group has a higher event rate
How does prevalence affect PPV and NPV? -
(Correct ANS)PPV increases with an increase in prevalence of disease in the study population
NPV decreases with increase in prevalence of disease in the study population
BANK LATEST 2025 -
COMPLETE QUESTIONS AND
ANSWERS.
Your All-in-One Practice Tool
USMLE Step 1 Biostatistics
__ exposure and outcome are measured simultaneously at a particular point of time (snapshot study).
-
(Correct ANS)Cross-section study
- prevalence study
- exposure and outcomes measured simultaneously
- surveys
__ is the tendency of the study population to affect the outcome since they are aware that they are
being studied. -
(Correct ANS)Hawthorne effect
__ or external validity pertains to the applicability of study results to other populations (the results of
a study in middle-aged woman would not be expected to be applicable to elderly men). -
(Correct ANS)Generalizability
___ bias occurs when the investigator's decision is adversely affected by knowledge of the exposure
status. -
(Correct ANS)Observer bias
___ can be applied to both disease pathogenesis and exposure to risk modifiers. Exposure to risk
factors and the initial steps in disease pathogenesis sometimes occur years before clinical
manifestations are evident. -
(Correct ANS)Latency period
___ design studies involve randomization to different interventions with additional study of 2 or more
variables. -
(Correct ANS)Factorial design
ex: study design that has 3 different drug interventions (metoprolol, ramipril, amlodipine) and 2
different variable BP endpoints
,___ is design is best for determine the incidence of a disease. Comparing the incidence of the disease
in 2 populations (with and without a given risk factor) allows for the calculation of relative risk. -
(Correct ANS)Cohort
___ is said to be successful when a similarity of baseline characteristics of the patients in the
treatment and placebo group is seen. -
(Correct ANS)Randomization
___ is statistical method that is commonly employed to compare the means of 2 groups of subjects. -
(Correct ANS)two-sample t test
___ is the measure of random error. The tighter the confidence interval, the more ___ the results. -
(Correct ANS)Precision
- increasing the sample size increases precision
___ is used to compare proportions. A 2x2 table may be used to compare the observed values with
the expected values. -
(Correct ANS)Chi-square test
___ when an external variable positively or negatively impacts the effect of a risk factor on the
disease of interest. -
(Correct ANS)Effect modification
A ___ test gives similar result on repeat measurements. -
(Correct ANS)Reliable test
- reliability is maximal when random error is minimal
ARR = -
(Correct ANS)a/a+b - c/c+d or (RR - 1)/RR
bias from errors of measurement -
(Correct ANS)information bias
bias from inaccurate recall of past exposure by subjects -
(Correct ANS)recall bias
bias from loss to follow up in prospective studies -
(Correct ANS)attrition bias aka selection bias
-achieve high rates of follow up to reduce potential for attrition bias
-other types of selection biases from innappropriate selection or poor retention of subjects:
ascertainment/sampling bias, nonresponse bias, berkson bias, prevalence bias
bias from patients exaggerating behavior, not admitting to something embarassing, claiming to take
meds when actually missing doses -
(Correct ANS)unacceptability bias
bias from the manner of selecting subjects for a study or from selective losses during follow up -
(Correct ANS)selection bias
bias from time differentials ie cancer screening prolongs survivial but actually just detecting earlier,
not improving treatment -
(Correct ANS)lead time bias
bias when people do not respond to phone calls or return surveys -
(Correct ANS)nonresponse bias; can cause error if nonresponders differ from responders; try to
contact nonresponders repeatedly, or list nonresponders as unknown in data analysis, never make up
responses
,bias when study sample is not representative of the target population with respect to exposure and
outcome -
(Correct ANS)sample distortion bias
bias when subjects affect their outcome since they know they are being studied -
(Correct ANS)hawthorne effect
tendency of study population to affect outcome because they are aware they are being studied and
change their behavior
bias where investigator is not blinded; decision is affected by knowledge of exposure status -
(Correct ANS)observer bias
-investigator decision adversely affected by knowledge of exposure status ie knowing the race of
patients in a study between ethnicity and ESRD ties disease reports more frequently to black patients
bias where outcome is obtained from a patients subjective and not by objective diagnostic methods -
(Correct ANS)respondent bias
Biostats 2x2 table -
(Correct ANS)
Calculate attributable risk percent (ARP). -
(Correct ANS)Excess risk in population that can be explained by exposure to particular risk factor
ARP = (RR - 1)/RR
Calculate risk. -
(Correct ANS)Divide the number of disease subjects by the total number of subjects (all the people at
risk)
Risk = probability of getting a disease over a certain period of time
calculating attributable risk -
(Correct ANS)AR = excess risk in a population that can be explained by exposure to a particular risk
factor; calculate by subtracting baseline risk in an unexposed population from the risk in an exposed
population, then divide result by risk in exposed
AR = risk in exposed - risk in unexposed / risk in exposed
*AR = (RR-1)/RR*
calculating negative predictive value -
(Correct ANS)people with a negative test who actually do not have the disease
NPV = true negatives / true negatives + false negatives
*NPV = D / D+C*
calculating positive predictive value -
(Correct ANS)people with a positive test who actually have the disease
PPV = true positives / true positives + false positives
*PPV = A / A+B*
calculating relative risk -
(Correct ANS)RR = a/(a+b) / c/(c+d)
case control vs retrospective cohort -
(Correct ANS)the order in which outcomes and risk factors are assessed
case control: find outcome first, then look for associated factors
retrospective: find risk factors first, then find outcome
, Common types of systemic error in statistical studies -
(Correct ANS)
confounding is defined as -
(Correct ANS)mixing up the effect of exposure with the effect of an extranous factor (confounder)
-extraneous factor must have some properties linking it with the exposure and outcome of interest
-must have properties linking it with the exposure and outcome
Correlation coefficient -1.0 and +1.0 -
(Correct ANS)r = + means increase one variable means increase in other
r = - means increase in one means decrease in the other
r = 0 means no correlation
correlation coefficient (r) meaning -
(Correct ANS)strength and direction of a linear association between 2 variables; - means changing in
opposite directions, + means positive correlation in the same direction
null = 0, no correlation
the closer r is to 1 or -1 the stronger the correlation
Different study designs -
(Correct ANS)
Distribution curves sensitive and specificity compare TN and TP. -
(Correct ANS)
effect modification -
(Correct ANS)an external variable affects the effect of a risk factor on the disease of interest
-distinguish it from confounding by performing a stratified analysis centered on the variable of
interest
-effect modification is not a bias but a natural phenomenon
effect of prevalence on PPV and NPV -
(Correct ANS)higher prevalence = higher PPV
lower prevalence = higher NPV
exposure odds ratio measurea association in __ studies where exposure of people with disease (cases)
is compared to those without disease (controls) -
(Correct ANS)case control
False negative ratio = ___. -
(Correct ANS)= 1 - sensitivity
False positive ratio = ___. -
(Correct ANS)= 1 - specificity
hazard ratio -
(Correct ANS)ratio of an event rate occuring in the treatment group compared to the non-treatment
group
<1 indicates treatment group has a lower event rate
>1 indicates treatment group has a higher event rate
How does prevalence affect PPV and NPV? -
(Correct ANS)PPV increases with an increase in prevalence of disease in the study population
NPV decreases with increase in prevalence of disease in the study population
