Behavioral Science Flashcards
formula for incidence rate
new cases/ population at risk
prevalence
all cases/ population at risk
point prevalence
all known cases of disease at certain point/total population at risk
crude mortality rate
deaths / populaitno
cause specific mortality rate
deaths from a cause/ population
case fatality rate
deaths from a cause/ all people with disease
proportion mortality rate
deaths from cause / all deaths
sensitivity
proportion of truly diseased people
Tp/(Tp+Fn)
false negative rate
1-sensitivity
specificity
people who do not have the disease
TN/(TN+FP)
false positive rate
1-specificity
positive predictive value
the person with a positive test really does have the disease
TP/(TP+FP)
negative predictive value
probability that someone with a negative test is a true negative
TN/(TN+FN)
formula for accuracy
(TP+TN)/(TP+TN+FP+FN)
reliability
the ability of a test to measure something consistently
validity
degree to which a test measure what is intended
selection bais
the sample selected doesn’t accurately represent the population
measurement bias
information is gathered in a way that distorts the information (using leading questions )
Hawthorne effect
when the subjects behavior is altered because they know they are being watched
experimenter expectancy (Pygmalion Effect)
the experimenters expectations are inadvertently communicated to the subjects who then give the desired effects
Lead time bias
give a false estimate of survival rates (early detection is confused with increased survival rates)
recall bias
subject fails to accurately recall events in the past
late look bias
individuals with severe diseases are less likely to be uncovered in a survey because they die first
confounding bias
factor being examined is related to other factors of less interest (example: comparing exercise and heart disease in two populations when one population is younger then the other )
design bias
parts of the study don’t fit together to answer the question of interest
cohort study
people who have been exposed to a risk factor versus those who have not
cross sectional study
presence or abscens of a disease and other variables
relative risk `
incidence rate of an exposed group divided by the incidence rate of an unexposed group (infant mortality in whites is 8 and in blacks its 18, divid 18 by 8 and get 2, blacks are twice as likely to die)