Question

(a) What is the relationship of the p-value and hypothesis testing?

(b) What is a p-value threshold of 0.05 mean? (in words)

(c) Why do you think that a p-value of 0.05 is used so often as a threshold? What is a situation when that value would be too large (i.e. a value much lower than 0.05 should be used)?

Answer 1

a) In hypothesis testing, the p-value or the probability value is the probability of obtaining observed results of a statistical hypothesis test, assuming that the null hypothesis is correct.Hypothesis testing tests validity of a claim depending on the p-value.

b) p-value varies from 0 to 1 just like any other probability value. P value 0.05 means there is 5 % chance or probability of having no significant difference or there is a 5% chance that the difference we have found isn’t really there.

c)p value of 0.05 means testing the hypothesis at a 5% level of significance.The threshold value of P<0.05 gives a high false discovery rate and it shows that either an exceptionally rare incident has occurred or the statement is false.That is why p value 0.05 is used so often as threshold value.

If we want to reduce the false discovery rate and want to be more sure about rejecting the null hypothesis ,then this threshold value can be lowered.