Biostats Flashcards
Mean
Average
Median
Middle value
Mode
Most frequent value
Sensitivity
People that have the disease with a (+) test
Specificity
People that don’t have the disease with a (-) test
PPV
Probability of having a disease with a (+) test
NPV
Probability of not having a disease with a (-) test
Incidence
New cases (rate per unit time)
Prevalence
Total cases (at one time)
Odds Ratio
Diseased are x times more likely to see risk factor
Confidence interval = 95%
95% sure it lies within the interval
Relative Risk
Risk of getting a disease with known exposure
NNT
Number needed to treat to change 1 life
p value
Random chance that you will be wrong 1 time out of 20
Null Hypothesis
Nothing happened
Power
Probability of detecting true intervention
Type I Error
P value errorFalse negativeToo optimistic
Type II Error
Power errorFalse positiveToo pessimistic
Accuracy
Validity (truth)
Precision
Reliability (keep making the same mistake)
Phases of Clinical Trials
I = Toxicity (hurt PT?)II = Efficacy (help PT?)III = Comparison (any better?)IV = Post-marketing surveillance (can they screw it up?)
Cohort Study
Prospective study that provides incidence (new cases)Uses relative risk
Case Control Study
Retrospective study that provides prevalence (total cases)Uses odds ratio
Cross Sectional Study
Provides a prevalence (snapshot)
Case Report
Describes an unusual PT
Case Series Report
Describes several unusual PTs
Consensus Panels
Panel of experts provide a recommendation
Clinical Wisdom
“I think…” paper
Meta-analysis
Tries to combine data from many trials
