Unit 10b: z-test, p-value, CI and REVIEW

Question 1

ways to tell if something is statistically significant

Answer 1

1) P VALUE

Probability of getting the results we did (or something more extreme)
if the null hypothesis were true
* Directly tells us if our result is “statistically significant”
* But you set your alpha (type 1 error rate first)
* If p < alpha, it’s statistically significant

2) CONFIDENCE INTERVALS

Question 2

effect size

Answer 2

Effect size tells you how meaningful the relationship between variables or the difference between groups is. A large effect size means that a research finding has practical significance, while a small effect size indicates limited practical applications

Question 3

why is effect size important

Answer 3

Even if the size of the difference is VERY small to the point of not
being meaningful, if your sample size is large enough, you’re very
likely to see significant results
* → Don’t rely too much on p-values
* → This is why you also want to report effect sizes to provide a sense
of how large the effect (in this case, the difference to the population
mean) is.
* (Also, the larger the effect size (or the difference), the smaller your
sample size needs to be to find a significant difference and vice versa)