In: Statistics and Probability
Linear Regression and Correlation.
x | y |
---|---|
2 | 4.64 |
3 | 6.76 |
4 | 3.08 |
5 | 5.5 |
6 | -5.88 |
7 | 1.04 |
8 | 0.56 |
9 | -2.42 |
Compute the equation of the linear regression line in the form y =
mx + b, where m is the slope and b is the intercept.
Use at least 3 decimal places. (Round if necessary)
y =_____ x + _____
Compute the correlation coeficient for this data set. Use at least
3 decimal places. (Round if necessary)
r= ____
Compute the P-value (Use HA: slope ≠ 0 for the
alternative hypothesis.)
Use at least 3 decimal places. (Round if necessary)
P-value = ____
At the alpha = 0.05 significance level, is the correlation
significant?
The following data are passed:
X | Y |
2 | 4.64 |
3 | 6.76 |
4 | 3.08 |
5 | 5.5 |
6 | -5.88 |
7 | 1.04 |
8 | 0.56 |
9 | -2.42 |
The independent variable is X, and the dependent variable is Y. In order to compute the regression coefficients, the following table needs to be used:
X | Y | X*Y | X2 | Y2 | |
2 | 4.64 | 9.28 | 4 | 21.5296 | |
3 | 6.76 | 20.28 | 9 | 45.6976 | |
4 | 3.08 | 12.32 | 16 | 9.4864 | |
5 | 5.5 | 27.5 | 25 | 30.25 | |
6 | -5.88 | -35.28 | 36 | 34.5744 | |
7 | 1.04 | 7.28 | 49 | 1.0816 | |
8 | 0.56 | 4.48 | 64 | 0.3136 | |
9 | -2.42 | -21.78 | 81 | 5.8564 | |
Sum = | 44 | 13.28 | 24.08 | 284 | 148.7896 |
Based on the above table, the following is calculated:
Therefore, based on the above calculations, the regression coefficients (the slope m, and the y-intercept n) are obtained as follows:
Therefore, we find that the regression equation is:
Y = 8.0714 - 1.1657 X
Therefore, based on this information, the sample correlation coefficient is computed as follows
which completes the calculation.
The following needs to be tested:
The sample size is n = 8 , so then the number of degrees of freedom is df = n-2 = 8 - 2 = 6
The corresponding t-statistic to test for the significance of the correlation is:
The p-value is computed as follows:
Since we have that p = 0.0685 ≥0.05, it is concluded that the null hypothesis H0 is not rejected.
Therefore, based on the sample correlation provided, it is concluded that there is not enough evidence to claim that the population correlation ρ is different than 0, at the 0.05 significance level.