Reading...
Play button
Play button
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;
9 Cards in this Set
- Front
- Back
|
Small study size = [wide/narrow] CI
May still be increased risk, study is too small to detect it |
wide
|
|
|
Large study = [wide/narrow] CI. but statistically significant risk may not be important biologically speaking
|
narrow
|
|
|
When we determine sample size/power, we must assume the [null/alternative] hypothesis
|
null
|
|
|
Null Hypothesis
|
There is an association between E and D
|
|
|
Type II Error is also called
|
Beta
|
|
|
TYPE I ERROR
|
occurs when null is rejected and it should not be.
so we say there is an association when one does not really exist |
|
|
TYPE II ERROR
|
occurs when we fail to reject the null and the alternative is actually true.
it is related to POWER so we say there's no association, when there actually is one |
|
|
POWER
|
is the probability of rejecting null and concluding that htere is a stat sig difference between the study groups if one really exists
POWER = 1 - (beta) |
|
|
What power is the accepted standard among epidemiologists?
|
.20
|
