eesohbel's version from 2016-08-11 01:49

Types of study

Question Answer
case controlcompares a group of people with a disease and without a disease. looks for risk factor. almost always retrospective.
case seriesdescriptive study that tracks patients with a known condition
cross-sectional studyassesses frequency of a disease at a point in time
prospective cohort studycompares a group with a given risk factor to a group without the risk factor to see if there is an increased likelihood of developing disease. can be either prospective or retrospective
cross over studysubjects are randomly allocated to a sequence of two or more treatments given consecutively. A washout (no treatment period) is often added between treatment intervals to limit cofounding effects
Cross sectional study measuresdisease prevalence
Case-control study measuresodds ratio (small number of people with rare disease)
cohort study measuresrelative risk (bigger number) looks to see if increased exposure increased likelihood of disease
odds ratio can be a close approximationrelative risk
cohort study best for determiningincidence of a disease. comparing incidence of disease in 2 populations allows for calculation of relative risk
cast control study best forcomparing risk factor frequency
cross section best forcomparing disease prevalence
critical distinction btwn case control and cohortcase control determines outcome first and looks for associated risk factor; cohort ascertains risk and then outcome

Clinical trial

Question Answer
triple blindingrefers to additional blinding of researchers analyzing the data
phase I study samplesmall number of healthy volunteers
purpose of phase I studyis it safe
phase II study samplesmall number of patients with disease of interest
phase II study purposedoes it work
phase III study samplelarge number of people randomly assigned either to the treatment or best available treatment
phase III study puproseis it good or better
phase IV study samplepost marketing surveillance of patients after treatment is approved
phase IV study purposecan it stay

Evaluation of diagnostic tests

Question Answer
sensitivitypercentage of people with a disease who test positive for the diseae
specificitypercentage of people with a disease who test negative
sensitivityTP/ (TP + FN)
specificityTN/(TN + FP)
what is PPVproportion of positive test results that are true positive
PPV equationTP/(TP+FP)
NPV equationTN/(TN+FN)
what is NPVprobability that person actually is disease free given a negative test result
low prevalencehigh NPV and low PPV
incidencenumber of new cases/number of people at risk
prevalencenumber of existing cases/number of people at risk
prevalence usually greater than incidencechronic diseases
prevalence = incidenceshort duration of a disease
case fatality ratenumber of fatal cases/ total number of people with the disease

Quantifying Risk

Question Answer
what is ODDS ratioodds that the group with the disease was exposed to a risk factor (a/c) divided by the odds that the group without the disease was exposed (b/d)
ODDS ratio(a/c)/(b/d)
what is relative riskrisk of developing disease in exposed group divided by risk in unexposed group
what is atributable riskthe proportion of disease occurences that are attributable to the exposure
Atributable risk percent(RR-1)/RR
what is absolute risk reductionthe difference in risk (not the proportion) attributable to intervention as compared to a control
number needed to treat1/ARR
number needed to harm1/AR
increased precisiondecreased standard deviation and increased statistical power
external validityresults hold true for populationn at large
internal validityresults hold true w/in the study
berkson biasstudy population selected from hospital is less healthy than general population
lead-time biasearly detection is confused with increased survival
confoundingrelationship between exposure and outcome is distorted due to third variable that is associated w/both exposure and outcome
effect modificationslightly different. variable actually enhances magnitude of risk factor for causign disease. example is estrogen and smoking
hazards ratioratio of an event occurring in treatment versus non treatment arm. ratios higher than 1 indicate treatment arm had higher rate of events


Question Answer
one standard deviation68%
two standard deviations95%
three standard deviations99.7%
tail to rightpositive skew
positive skewmean>median>mode
tail to leftnegative skew
negative skewmean
null hypothesishypothesis of no relationship or difference
alternative hypothesisthere is a relationship
if p value is less than .05reject the null and accept the alternative
type II erroroccurs when researchers accept null hypothesis when it is false. Aka a relationship exists!
type I errorwhen researchers reject the null, but the null is true. There is no relationship!
power (1-B)probability of rejecting a null hypothesis when it is truly false. Typically set at 80% and depends on sample size and difference between outcomes
CIwidth of CI determines power of study
the tighter the CImore precise the result
if the CI between 2 mean variables includes 0there is no significant diffference and accept the null
if CI for odds ratio or relative risk includes 1accept the null. there is no relationship
if CI for relative risk is greater than 1there is increased risk
if CI for relative risk is below 1there is decreased risk
if CI between 2 groups does not overlapstatistically significant difference exists
if CI between 2 groups does overlapusually no significant difference exists
t-testchecks differences between means of two groups
ANOVAchecks difference between means of three or more groups
CHI squared testchecks difference between categorical variables, percentages or porportions
r=1perfect correlation between two variables
r=-1no relationship between two variables
r>0there is a positive relationship between two variables
r<0there is a negative relationship between two variables
type II errorbeta
type I erroralpha


Question Answer
PPV and prevalence association?PPV increases with increasing disease prevalence and decreases with decreasing disease prevalence
NPV and prevalence association?NPV decreases with increasing disease prevalence and increases with decreasing disease prevalence
type I erroralpha. rejecting the null hypothesis when it is actually true
type II errorbeta. accepting the null hypothesis when it is actually false
P < alphaideal, this is statistically significant and means rejecting the null
P > alphafail to reject the null hypothesis
R = 1perfect correlation
R = 0no correlation at all
R > 0+ correlation so positive slope
R < 0- correlation so negative slope
1 standard deviation68%
2 standard deviations95%
3 standard deviations99.7%
how does a larger sample size affect power?increases power
how does a larger sample size affect Confidence Interval?decreases confidence interval
precision is akin toreliability
accuracy is akin to validity
what factors make something reproducible?precision and reliability
what factors make something compared to the gold standardaccuracy and validity
standard error of meanSD / sq rt of sample size
confidence intervalmean +/- Z (SEM)
Z value?1.96 for 95% ; 2.58 for 99%
incidencenumber of new cases / number at risk
prevalence number of existing cases / total population
positive skewmode < median < mean (R skew)
negative skewmode > median > mean (L skew)


Question Answer
which study type looks at odds ratio?case control
what does case control find?odds ratio
what studies find relative risk?RCT or cohort
what do cohort studies find?relative risk
what do RCT studies find?relative risk
what do cross sectional studies find?disease prevalence
what studies find disease prevalence?cross sectional
snap-shot in timecross sectional
no controlscase series
when prevalence is low, what happens to OR and RR?they become more equal
how do you increase precision?decrease standard deviation and increase statistical power
most affected by outliers?mean
least affected by outliers?mode
primary disease preventionprevent (vaccination, condoms)
secondary disease preventionscreening (pap)
tertiary disease preventiontreatment (chemo)
phase I trialtoxicity, safety, pharm dynamics and kinetics
phase II trialefficacy, dosing, adverse effects
phase III trialcompare to standard
phase IV triallong term adverse effects
OR(a/c) / (b/d) OR ad/bc
RRa/a+b / c/c+d
ARa/a+b - c/c+d
ARRc/c+d - a/a+b
failure of precisionrandom error
failure of accuracysystematic error
reproducibility of test resultsprecision aka reliability
the test measures what it is supposed toaccuracy aka validity
disease specific mortalitynumber of fatal cases/total population
case fatality ratenumber of fatal cases/# of people with disease
external validityresults hold true for population at large
internal validityresults hold true within study


Question Answer
study population selected form hospital is less healthy than general populationberkson bias (selection bias)
study population is healthier than general populationhealthy worker effect (selection bias)
participating subjects differ from nonrespondents in meaningful waysnon-response bias (selection bias)
awareness of disorder alters recall by subjectsrecall bias
common in retrospective studiesrecall bias
information is gathered in a way that distorts itmeasurement bias
subjects in different groups are not treated the sameprocedure bias
researchers belief in the efficacy of treatment changes the outcomepygmalion effect (observer-expectancy bias)
factor is related to both exposure and outcomeconfounding bias
early detection is confused with increased survivallead time bias
reduce selection bias?randomization
reduce recal bias?decrease time from exposure to follow up
reduce measurement bias?use standardized method of data collection
reduce procedure bias or pygmalion effect?blinding and placebos
reduce confounding bias?multiple repeated studies, crossover studies, matching
reduce lead time bias?measure back-end survival
change in behavior in a study group resulting from knowing they are being observedhawthorn effect

Recent badges