Biostatistics
Terms
undefined, object
copy deck
- a study that is chosen based on presence or absence of disease and then information collected about risk factors
- case-control study
- a cohort study is what kind of study?
- observational
- in this type of study, the sample is chosen about presence or absence of risk factors and subjects are followed over time for development of disease
- cohort study
- define prevalence
- total cases in population at a given time/ total population
- define incidence
-
new cases in population over a given time period/total population at risk during that time
incidence is new incidents - for what type of diseases is prevalence greater than incidence?
- chronic diseases
- for what type of diseases does prevalence equal incidence?
- acute diseases
- for what type of test is high sensitivity desirable?
- screening
- define sensitivity and give formula
- number of true positives divided by number of all people with the disease: a/a+c
- how do you calculate the false negative rate?
- 1-sensitivity
- for what type of test is high specificity desirable for?
- confirmatory test
- define specificity and give formula
- number of true negatives divided by number of all people without the disease: d/b+d
- 1-specificity is equal to what?
- false positive rate
- what is positive predictive value and how do you calculate it?
- probability of havinig a condition given a positive test - number of true positives divided by number of people who tested positive for the disease: a/a+b
- what is negative predictive value and how do you calculate it?
- probability of having a condition given a negative test - number of true negatives divided by number of people who tested negative for a disease: d/c+d
- which are dependent on the prevalence of disease: sensitivity/specificity or predictive values?
- predictive values
- when prevalence is higher, what increases?
- positive predictive value
- when prevalence is lower what increases?
- negative predictive value
- what is an odds ratio?
- odds of having disease in exposed group divided by odds of having disease in unexposed group (odds calculated within group as number with disease divided by number without disease)
- what is the formula for odds ratio?
- (a/b)/(c/d) = ad/bc
- what is relative risk?
- disease risk in exposed group dividd by disease risk in unexposed group - risk is calculated within a group as number with disease divided by total number of people in group
- what is the formula for relative risk?
- a/(a+b)/c/(c+d)
- what is a type I error?
- stating that there is an effect when none exists; equal to p
- what is a type II error?
- stating that there is not an effect of difference when one exists (power= 1-type II)
- what does Z equal for the 95% confidence interval?
- 1.96
- what is the formula for confidence interval?
- CI=range from (mean-Z(SEM) to (mean+Z(SEM)
- what does standard error of the mean equal?
- standard deviation/square root of n
- a t-test checks the difference between what?
- the means of 2 groups
- what does ANOVA check?
- the difference between the means of 3 or more groups
- what does chi square check?
- difference between 2 or more percentages or proportions of categorical outcomes (not means)
- mean > median > mode is what kind of skew?
- positive - tail on right
- mean < median < mode is what kind of skew?
- negative - tail on left