How do one tailed and two tailed hypothesis tests differ

A one tailed test is when you are testing specifically for an increase or decrease- eg whether the probability of a person buying a product has INCREASED after a marketing change

A two tailed test is when you are testing for a change (increase OR decrease)- eg whether the use of a different type of feed has affected the average weight of chickens

Because the level of significance given in a question is the probability of rejecting null hypothesis if it were true, in a two tailed test the critical region exists at both ends of the distribution curve - the total area in the critical region must equal the level of significance - so if the level of significance was 10%, the critical region at either end must be 5% so that the total probability of results being in the critical region under the null hypothesis is 10%

In a one tailed test the critical region is only at one end of the distribution curve so does not need to be divided by two

KG

Related Maths A Level answers

All answers ▸

What is the tangent line to the curve y = x^3+4x+5 at the point where x = 2?


Why is it that the sum of all natural numbers up to n is 1/2(n)(n+1)?


Let y(x) be a function with derivative y'(x)=x^2-2 and y(0) =7. What is the value of y at x = 3?


Prove that 2Sec(x)Cot(x) is identical to 2Cosec(x)