The 365 Data Science team is proud to invite you to our own community forum. A very well built system to support your queries, questions and give the chance to show your knowledge and help others in their path of becoming Data Science specialists.
Anybody can ask a question
Anybody can answer
The best answers are voted up and moderated by our team

Hypothesis Testing: Null Hypothesis and Alternative Hypothesis

Hypothesis Testing: Null Hypothesis and Alternative Hypothesis

Super Learner

In the statistic course, Hypothesis testing section, I do not understand what it means to reject H0 at 5% and accept it at 1% significance level. There is this magnesium pill example where the H0: Mean before >= Mean after, and H1: Mean before < Mean after. This basically means that H0: the magnesium pill is not working, H1: the magnesium pill is working. Then after the calculation we get that P-value is 0.024 so at 5% significance level we reject H0 (so the magnesium pill is working) and at 1% level we accept H0 (so the magnesium pill is not working)
Does this mean that it is 2,4% that we believe the pill is working but in reality it does not? 
Thank you in advance :).

1 Answer

365 Team

Hi there,
The p-value shows the highest level of significance at which we can reject the null hypothesis.
If 2.4% is a level of significance which is good enough for you, then you can conclude that the pill is working.
Most often, we pick a significance level of 5% and compare the p-value with it. 
The 365 Team

Complete Data Science Education
Get 50% OFF