STATS Flashcards
Equation for positive predictive value:
TP / TP + FP
Equation for negative predictive value:
TN / TN + FN
Equation for sensitivity:
TP / TP + FN
Equation for specificity:
TN / TN + FP
Equation for number needed to treat:
1 / absolute risk reduction
What is precision?
A tests ability to produce the same measurements with repeated tests.
What is sensitivity?
SNOUT: high sensitivity, rules something out.
Likelihood of a positive result being a true positive.
Equation for absolute risk reduction:
ARR = Experiment risk - control risk
Equation for power and what it’s used for:
1 / probability of a type II error
Establishes how large the sample size needs to be.
Type I error:
Rejecting a true null hypothesis
Standard error of the mean:
Standard deviation / square root of n
How accurate the calculated sample mean is compared to the true population mean
Standard deviation explained:
1 SD away from the mean on either side of a normal distribution = 68% of cases.
2 SD = 95%
3 SD = 99%
Main bias in case-control studies:
Recall bias
What graph is done to represent if there is publication bias?
Funnel plot
Definition of bias:
Systematic differences between the data and reality of the population
Incidence =
Number of new cases per population in a given time period
Prevalence =
Total number of cases per population in a given time period
In chronic diseases, prevalence»_space; incidence.
In acute diseases, prevalence ~ = incidence
Tests use to determine differences between a) 2 and b) >2 groups in parametric data:
T-Test
ANOVA
What is the chi-squared test used for?
To see if there is a significant difference between 2 groups of categorical data.
Compares the observed data with data that would be expected if the null hypothesis were true.
Which graph shows the results of meta-analysis?
Forest plot
What does the p-value represent?
The probability of obtaining a result by chance at least as extreme as the one actually observed.
Small p-value = better, as less likely that the result has come about by chance, and is actually due to the intervention in the study.
What does meta-analysis do to the power and the p-value of studies?
Increases the power.
Decreases the p-value.
Which kind of study is observational and prospective, and what is the usual outcome measure?
Cohort study
Relative risk
What kind of study is observational and retrospective, and what is the usual outcome measure?
Case-control study
Odds ratio = odds in exposed group / odds in unexposed group
