Statistics Flashcards
what are P values?
numbers between 0-1 that quantify how confident we should be that drug A is different from drug B
which P-value shows the most confidence?
P values closer to 0
what is the accepted P-value?
0.05% (95%)
a small p-value when there there is no difference is called…?
a false positive
what are examples of dichotomous variables? (2)
- employed vs unemployed
- has disease vs does not have disease
what is a reference population?
extracting a sample of a larger population
what is the null hypothesis?
a statement that there is no relationship between the two variables that are tested
what is the confidence interval?
range of values in which the actual value lies
what is a type 1 error?
rejecting the null hypothesis when it is true
what is a type 2 error?
accepting the null when it is false
what does the box size represent on a forest plot?
the weight of the study
what does the vertical line represent on a forest plot? (2)
- the line of no effect
- intervention has had no effect on outcome
what does the horizontal line represent on a forest plot?
confidence interval
what does the diamond represent on a forest plot?
the total meta-analytic result
what does the peak of the diamond represent on a forest plot?
optimal result
what does the sides of the diamond represent on a forest plot?
confidence intervals
what is heterogenity?
differences between studies not due to chance
what are the types of heterogenity? (2)
- clinical
- statistical
what test is used for heterogenity?
chia-squared test
what is a study population?
small sample of the entire population
what is the confidence interval?
intervals computed from the sample data, which were the study repeated multiple times, would contain the true effect 95% of the time
what is relative risk?
comparing the probability of the event occurring to all possible events considered in the study
how is relative risk calculated?
incidence in exposed / incidence in non exposed
what does it mean if the relative risk = 1?
incidence in exposed group is the same in non exposed
what does it mean if the relative risk > 1?
incidence in exposed group is greater than in non exposed
what does it mean if the relative risk < 1?
incidence in exposed group is lower than in non exposed
“the further the relative risk is from 1…
…the stronger the association”
which study can you not use relative risk in?
case control
what is the odds ratio?
a measure of how strongly an event is associated with exposure
how do you calculate odds ratio?
odds the case was exposed / odds the control was exposed
what does it mean if the odds ratio = 1?
exposure is not associated with disease
what does it mean if the odds ratio > 1?
exposure is positively associated with disease
what does it mean if the odds ratio < 1?
exposure is negatively associated with the disease
“the further the odds ratio is from 1…
…the stronger the association”
which studies can you use odds ratios in? (2)
- cohort
- case controls