Term
| steps in statistical testing |
|
Definition
- hypothesis generation (null and alternative)
- computing measures of association
- obtaining a probability value (P value)
- calculate 95% confidence interval
|
|
|
Term
|
Definition
- prospective study- rates of disease same between exposed and unexposed (RR = 1)
- case control study- no difference between case and controls with regard to exposure of interest (OR=1)
|
|
|
Term
|
Definition
- probability of observing a measure of association stronger than the one observed if the null hypothesis is true
- small p value means its unlikely to observe such a measure of association if the null hypothesis is true
- by convention, when p is less than 0.05, we reject null hypothesis
|
|
|
Term
| CI: value in order to reject null hypothesis |
|
Definition
| confidence interval for RR or OR cannot cross 1.0 |
|
|
Term
| Interpret p value of 0.005 |
|
Definition
probability of obtaining a RR less than 0.7 if the null hypothesis is true is 5 in 1000 |
|
|
