In: Statistics and Probability
Given a linear correlation coefficient r = 0.476, a sample size n = 20, and a significance level of α = 0.05, use Table A-6 to determine the critical value of r and state if the given r represents a significant linear correlation. Would your answer change if the significance level was α = 0.01?
CASE 1 - When α = 0.05
Let ρ = population correlation
coefficient (unknown)
r = sample correlation coefficient (known; calculated from sample
data)
Null and Alternative hypothesis:
H0:ρ=0 i.e. population correlation coefficient is 'close to
0'
HA:ρ≠0 i.e. population correlation coefficient is 'significantly
different from 0'
Value of correlation coefficient:
r=0.476
Degrees of freedom
The sample size is n=20, so then the number of degrees of freedom
is df = n-2 = 20 - 2 = 18
Table of Critical Values Method
Critical region:
The corresponding critical correlation value rc for a significance
level of α=0.05, for a Two-tailed test is: rc=0.4438
Rejection Region
Observe that in this case, the null hypothesis H0:ρ=0 is rejected
if |r|>rc=0.4438.
Decision about the null hypothesis
Based on the sample correlation provided, we have that
|r|=0.476>rc=0.4438, from which is concluded that the null
hypothesis is rejected.
CASE 2 - When α = 0.01
Let ρ = population correlation
coefficient (unknown)
r = sample correlation coefficient (known; calculated from sample
data)
Null and Alternative hypothesis:
H0:ρ=0 i.e. population correlation coefficient is 'close to
0'
HA:ρ≠0 i.e. population correlation coefficient is 'significantly
different from 0'
Value of correlation coefficient:
r=0.476
Degrees of freedom
The sample size is n=20, so then the number of degrees of freedom
is df = n-2 = 20 - 2 = 18
Table of Critical Values Method
Critical region:
The corresponding critical correlation value rc for a significance
level of α=0.01, for a Two-tailed test is: rc=0.5614
Rejection Region
Observe that in this case, the null hypothesis H0:ρ=0 is rejected
if |r|>rc=0.5614.
Decision about the null hypothesis
Based on the sample correlation provided, we have that
|r|=0.476<rc=0.5614, from which is concluded that the null
hypothesis is NOT rejected.
Let me know in the comments if anything is not clear. I will reply ASAP! Please do upvote if satisfied!