Science of Practice Flashcards
What is a Chi-squared test?
Non-parametric test of statistical significance for bivariate tabular analysis - enables analysis between 2 categorical variables
What is a Student’s t-test
Compares data that is fully paired or matched - usually before and after measurements of the same variable or how a single group of test participants did under 2 different test conditions
What is Kendall’s rank correlation?
Nonparametric measure of strength and direction of association that exists between 2 variables measured on a scale
What is linear regression?
Linear relationship between 2 variables but does not allow analysis if this could have occurred by chance
What is incidence?
Rate of new disease cases occurring within a population over a specified period
What is negative predictive value?
Chance the patient definitely does not have the condition if the test is negative
What is Parametric Pearson’s correlation coefficient?
Describes how well a set of data fits the proposed regression line but does not allow analysis to see if this could occur by chance
What is positive predictive value?
Chance the patient definitely has the condition if the test is positive
What is a two-sample t-test?
Compares the means of 2 groups of normally distributed data and continuous data
What is a case control study?
Investigates potential associations between exposures and outcomes especially when the outcome is rare.
What is an odds ratio?
The odds of an individual with a disease having been exposed to a risk factor, divided by the odds that a patient without a disease having been exposed to the risk factor.
What is Fishers exact test?
Used where data is categorical rather than continuous.
What is precision?
Closeness of agreement between independent test results - evaluated consistency and reliability of a test in producing similar outcomes if reproduced
What is the Mann-Whitney U test?
Comparing 2 independent groups, especially when samples sizes are small. Does not assume a normal distribution of data.
What is a parallel trial?
2 separate treatment groups running consecutively and then compared. Each patient is exposed to a single treatment option only.