3 - Intro to Stats Flashcards
What does a small sample population mean?
- Low level of precision
What words shouldn’t you use when making conclusions?
’ inaccurate, inexact, invalid ‘
Say results due to chance, bias or confounding variable
How would you find true or underlying value?
What is a hypothesis and how is it tested?
Hypothesis test - Make a statement about the probability of observed data at least as extreme as that observed if the stated hypothesis is true, allows us to decide whether to reject or not
How do you interpret p values for hypothesis testing?
What are the limitations with p values for hypothesis testing?
- p = 0.05 is arbitary, one could be 0.049 and other could be 0.051, not much difference but one significant and one not
- Statistically significant /= clinically important
- Statistical significance depends on sample size
What is a null hypothesis and how do you interpret it?
Hypothesis assuming there is no significant difference between two groups
- p < 0.05 strongly suggests hypothesis is false
- p > 0.05 data is consistent with null hypothesis but not proven
What are 95% CI?
Measure of precision of observed values
Where does observed values lie in stats tests?
ALWAYS LIE WITHIN 95% CI, IN THE MIDDLE
What are the values inclusive of 95% CI said to be?
Consistent with the data
What makes the 95% CI wider?
- Smaller sample size
- Greater variation in population values
What is the value of the null hypothesis if true?
- 0 if looking at difference/reduction
- 1 if looking at ratios
