On p-value

CFA Level I Quant
#1

I chanced upon this question:

A two-tailed t-test of the null hypothesis that the population mean differs from zero has a p-value of 0.0275. Using a significance level of 5%, the most appropriate conclusion is: A. reject the null hypothesis. B. accept the null hypothesis. C. the chosen significance level is too high. Answer = A A is correct. The p-value is the smallest level of significance at which the null hypothesis can be rejected. In this case, the given p-value is less than the given level of significance and we reject the null hypothesis. Just wondering: When they quote p-value, do we assume 2 sided p-values ? Because i took 5% sig level and divdided by 2, and answered B instead of A. Since 0.0275 < 0.025.

#2

The p-value and significance level account for the total margin of error.

#3

what do you mean? sorry i don’t quite understand.

Why don’t we use the significance level of 1.96?

#4

P-value has nothing to do with two tailed test they put that there to confuse you. If p-value is less than significance level, reject.

#5

and the P-value in this case is 0.05? Because if it’s 0.025 then P-value > significance level.

#6

You simply compare the (unaltered) p-value to the (unaltered) level of significnace.

Here, you compare 2.75% to 5%.

If they’d changed it to a one-tail test (and left everything else the same), you’d still compare 2.75% to 5%.

#7

geez, you saved the day again S2K…thanks!

thanks to everyone here and faptor for the posting too. There’s your answer!

#8

My pleasure.

#9

Noted. Thanks again! Greatly appreciated.

#10

You’re most welcome.

#11

since it is two tailed test divide both values by 2 and you will get p-value=.0275/2=0.01375 which is less than CV, 0.05/2=0.025. since pv<cv i.e. 0.01375<0.025, reject the null hypothesis. That’s it…