In: Statistics and Probability
Answer)
Null hypothesis Ho : u = 0.2 (20%)
Alternate hypothesis Ha : u is not equal to 0.2 (20%)
Claimed p = 0.2
Observed p = 36/240 = 0.15
N = sample size = 240
First we need to check the conditions of normality.
If np and n(1-p) both are greater than 5 or not.
n*p = 36
n*(1-p) = 204
As both are greater than 5, we can use standard normal z table to conduct the test.
Test statistics z = (observed p - claimed p)/standard error
Standard error = √claimed p*(1-claimed p)/√n
Z = -1.94
P(z<-1.94) = 0.0262
But this is for one tail and our test is two tailed
So,the required p-value is = 2*0.0262 = 0.0524
As the obtained p-value is less than the given significance level, 0.1 (1%)
We reject the null hypothesis.
So, we have enough evidence to support the claim that proportion is different.
Type 1 error means, rejecting true null hypothesis.
Type 2 error means, failure to reject the false null hypothesis
Here, observed p is 0.15
And claimed is 0.20
And they both are different, so our conclusion is right.