Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
17 Cards in this Set
- Front
- Back
binary variable
|
a variable with only two values
|
|
continuous variable
|
a variable in which the numbers act as numerical values.
ex: age, birth weight also called quantitative variable |
|
nominal variable
|
categorica variable where the categories are unordered.
E.g.: gender, birth type |
|
ordinal variable
|
categorical variable where the categories imply an order on some continuum (e.g., level of health problems)
|
|
Type I Error
|
rejecting the null hypothesis when it is true
concluding there is a difference when there is not called alpha |
|
level of significance of the test
|
probability of committing a type I error
|
|
Type II Error
|
accepting the null hypothesis when it is false
concluding there is no difference when there is one called beta |
|
power of the study
|
ability to detect a difference if a true difference exists
i.e., probability of rejecting null hypothesis when it is false 1 - beta beta usu. = 0.2, so power = 80% |
|
p-value
|
the probability that an observed association is due to chance
|
|
logistic regression
|
outcome of interest is binary
allows adjustment for confounding variables provides direct estimate of odds ratio for each indep. variable |
|
correlation coefficient
|
measures strength of association btwn 2 continuous variables
between -1 and 1 not equal to slope of line |
|
Kaplan-Meier plot
|
survival vs. time
each "step" represents an outcome event |
|
multiple regression
|
like linear regression but allows multiple independent variables
can be used to adjust for confounders |
|
case fatality
|
(deaths due to a disease) / (number of people with that disease)
|
|
absolute risk difference
|
difference between risk of outcome in exposed group and risk in unexposed
|
|
number needed to treat (NNT)
|
1/ARD
|
|
Cox Proportional Hazards Regression
|
similar to other multiple regressions
form of survival analysis assesses independent effect of multiple variables on survival can predict rate at which outcomes will occur estimates relative risk |