1. State the Hypothesis
H0: u=10
H1: u<10
1. State the Hypothesis
H0: u=10 (The average customer spends $10 and the bar should close)
H1: u>10 (The average customer spends more than $10 and the bar should remain open)
Interpret the following in the context of the problem.
The null hypothesis is true.
The average customer spends $10.
What is the lowest possible p value?
0
2. Gather the data
x̄ = $11.24
s = $5.69
n = 30
Here, x̄ is the average amount of money spent by all customers
2. Gather the data
x̄ = $11.24
s = $5.69
n = 30
Here, x̄ is the average amount of money spent by the customers in our sample
Interpret the following in the context of the problem.
We reject the null hypothesis.
We believe the average customer spends more than $10.
What is the highest possible p value?
1
3. We first assume that the null hypothesis is true
We assume that the average customer spends less than $10.
3. We first assume that the null hypothesis is true
We assume that the average customer spends $10
What would a type I error be in this scenarior?
We believe the average customer spends more than $10 when they in reality do not.
What would the result of a hypothesis test be if the significance level was 1?
4. Use the Central Limit Theorem
x̄ ~ N(11.24,0.19)
3. Use the Central Limit Theorem
x̄ ~ N(u,s/sqrt(n))
x̄ ~ N(10,5.69/sqrt(30))
x̄ ~ N(10,1.04)
95%
What would the result of a hypothesis test be if the significance level was 0?
The hypothesis test would always fail to reject.
5. Draw a picture of the distribution of the sample averages
see photos
5. Draw a picture of the distribution of the sample averages
Because we are using a alternative hypothesis H1:u>10 we should shade in the area to the right of the sample average
What would power be in this scenario?
Power is the ability to correctly reject a false null hypothesis.
Power is the ability to correctly conclude that the bar should remain open when the average customer does spend more than $10.
When would the p value of a hypothesis test with a not equal to alternative hypothesis be 1?
When the null hypothesis is the sample average