NBME biostat q

[MudPhud20XX]

I am really bad at this kind of biostat q. I just know the definitions of type 1 and II error superficially and I feel like I really have no grasp on this kind of question. Can anyone walk me through this question? I would really appreciate any help.

A paper says "We chose the sample size to have an 80% power of detecting a 15% mean difference with a significance level (two-sided) of 5%" If there really is no diffidence between the groups overall, which of the following best represents the chance that the study will find a statistically significant difference, and what is the error called?

A. 0% type 1 error
B. 0% type II error
C. 5% type I error
D. 5% type II error
E. 15% type 1 error
F. 15% type II error
G. 20% type I error
H. 20% type II error

so all I know is that since there is really no difference it has to be type 1 alpha error, right? How do I approach the next step?

---

Members don't see this ad.

 

[Missorleans]

Is the answer C? It tells you the significance level is 5%, so that's your alpha, the probability of rejecting the null when it is true. The question wants to know what the error is called when you find that the null is false when it's actually true (there is no difference). You correctly identified that as type I error. Next you need to remember that the type I error rate is alpha, the significance level.

 

[SBR249]

power always denotes 1-beta with beta being the probability of making a type II error. Significance usually means p-value which is the probability of making a type I error. In this case, finding a difference where none exists is erroneously rejecting the null hypothesis which is a type I error which means you have to look at the p-value which is the probability that a statistically significant result will occur by random chance in this case it's 5%.