In: Statistics and Probability
Subject X Y
1 18 22
2 13 19
3 25 35
4 16 24
5 27 56
6 16 25
7 9 30
With an alpha level of .05 and a two-tail test, what would be a significant correlation coefficient for the above scores (what is the critical value)?
Question options:
.729
.7545
.789
.6664
r Critical is the minimum value of r that would be considered significant for a given sample size and alpha level. r Critical is usually looked up on a chart but can be calculated directly with the Excel formula.
Using chart:
The critical value of the Pearson product moment correlation coefficient for the degree of freedom of n - 2 = 7 -2 = 5 and alpha = 0.05 and a two-tailed test can be looked up from the critical r table, we find the critical value to 0.7545.
Using EXCEL
I have used EXCEL Addin Real statistics to find the correlation coefficient of X and Y.
EXCEL> AddIn> Real Statistics > Data Analysis > Corr > Correlation Tests
Input Range 1: Select data of X
Input Range 2: Select data of Y
Alpha =0.05
Test Type: Pearson's
Number of Tails: 2
Ok
Correlation Coefficients | |||||
Pearson | 0.7 | ||||
Spearman | 0.5 | ||||
Kendall | 0.4 | ||||
Pearson's coeff (t test) | Pearson's coeff (Fisher) | ||||
Alpha | 0.1 | Rho | 0 | ||
Tails | 2 | Alpha | 0.1 | ||
Tails | 2 | ||||
corr | 0.7 | ||||
std err | 0.3 | corr | 0.7 | ||
t | 2.3 | std err | 0.4 | ||
p-value | 0.1 | z | 1.8 | ||
lower | -0.1 | p-value | 0.1 | ||
upper | 1.5 | lower | -0.1 | ||
upper | 1 |
We get the Pearson's correlation coefficient, r of 0.72128 which is not significant at 5% level of significance as two-tailed p-value is 0.06733 which is more than 0.05 and with a t-statistic value of 2.32855. The critical t-value for df = n -2 = 7-2 and alpha = 0.05 is 2.570543. Also, the r value is less than the critical r -value.