In: Statistics and Probability
Lucy always uses an alpha level of 0.01 (two-tailed). Charlie always uses an alpha level of 0.05 (two-tailed). Which researcher is more likely to make a Type I Error. Lucy or charlie?
A researcher is interested in whether blood pressure decreases among adults who eat dark chocolate. The mean systolic blood pressure of the population is 135 with a standard deviation of 15. She tests a sample of 100 adults who eat dark chocolate and finds their mean systolic blood pressure to be 120. What is the null hypothesis?
μ = 135 |
||
μ ≠ 135 |
||
μ > 135 |
||
μ ≥ 135 |
According to Cohen's d conventions, which of the following would be considered to be a medium effect size?
-0.55 |
||
0.81 |
||
-0.98 |
||
0.17 |
With α = 0.05, what is the critical t value for a one-tailed test with n = 15?
t = 1.761 |
||
t = 1.753 |
||
t = 2.145 |
||
t = 2.131 |
What z-score values form the boundaries for the middle 68% of a normal distribution?
z = +0.2 and z = - 0.2 |
||
z = +0.4 and z = - 0.4 |
||
z = +0.8 and z = - 0.8 |
||
z = +1.0 and z = - 1.0 |
Solution:
Question 1)
Lucy always uses an alpha level of 0.01 (two-tailed).
Charlie always uses an alpha level of 0.05 (two-tailed).
Level of significance is nothing but P( Type I Error)
So as alpha level increases, P( Type I Error) increases.
thus
Charlie researcher is more likely to make a Type I Error.
Question 2)
The mean systolic blood pressure of the population is 135 with a standard deviation of 15.
that is:
A researcher is interested in whether blood pressure decreases among adults who eat dark chocolate.
thus this is left tailed test, thus H1 is < type
then null hypothesis H0 would be ≥ type.
Thus correct answer is:
μ ≥ 135
Question 3)
A Cohen's d value close to 0.5 is considered as medium effect.
Thus from given options: -0.55 , we use absolute value = 0.55 close to 0.5
hence 0.55 has medium effect
thus correct answer is:
-0.55
Question 4)
With α = 0.05, what is the critical t value for a one-tailed test with n = 15?
df = n - 1 = 15 - 1 = 14
One tail area = 0.05
t = 1.761
Question 5)
What z-score values form the boundaries for the middle 68% of a normal distribution?
According to Empirical rule:
68% of the data falls within 1 standard deviation from mean
thus z values are: -1.00 and 1.00
thus correct answer is:
z = +1.0 and z =
- 1.0