epidemiology Flashcards
observational studies
investigator passively observes as nature takes its course
interventional studies
investigator actively manipulates study participants- randomized controlled trials
process of hypothesis testing
1) set up the hypothesis [association]
2) state the null hypothesis [no association]
3) summarise the data
4) interpret the probability of no association
probability
the chance of a particular event happening
probability of 0- null hypothesis is definitely not true
probability of 1- null hypothesis is definitely not true
p-value cut off
common convention to use a p-value cut off of 0.05
- if the prob is less than 1 in 20 [0.05] it is unlikely that Ho is true, reject null hypothesis
- is prob is more than 1 in 20 [0.05], it is likely that Ho is true, accept null hypothesis
chance
a p-value tells us how likely it is that the result of a study would have occured by chance if the null hypothesis was true
bias
any systematic error in a study that results in an incorrect estimate of the association between exposure and risk
selection bias
any error in a study that results in an incorrect estimate of identifying the study population
observation [information bias]
any systematic error in the measurement of information on the exposures/outcomes
confounding
a mixing of effects between exposure, the outcome and a third factor that is associated with the exposure and independently affects the risk of developing the disease
reverse casualty
X and Y are associated, but not in the way you expect- instead of X causing Y, Y causes X
simultaneity
X causes Y and Y causes X
bradford hills criteria for inferring casuality
1) strength of association
2) consistency
3) specificity
4) temporality
5) dose-response relationship
6) plausibility
7) coherence
8) reversibility