A researcher would like to predict the dependent variable Y from the two independent variables X1 and X2 for a sample of N=10 subjects. Use multiple linear regression to calculate the coefficient of multiple determination and test statistics to assess the significance of the regression model and partial slopes. Use a significance level α=0.05.
X1 | X2 | Y |
---|---|---|
31.9 | 50.2 | 89.2 |
12.7 | 25.5 | 33.5 |
41.2 | 46.4 | 44.5 |
29.2 | 42.9 | 76.3 |
22.9 | 36.6 | 56 |
39.4 | 46.6 | 55.3 |
36.4 | 46.2 | 43 |
56.1 | 49.6 | 7.6 |
21 | 39.7 | 58.2 |
58 | 48.3 | 22.6 |
R2=
F=
P-value for overall model =
t1=
for b1, P-value =
t2=
for b2, P-value =
What is your conclusion for the overall regression model (also called the omnibus test)?
- The overall regression model is statistically significant at α=0.05.
- The overall regression model is not statistically significant at α=0.05.
Which of the regression coefficients are statistically different from zero?
- neither regression coefficient is statistically significant
- the slope for the first variable b1 is the only statistically significant coefficient
- the slope for the second variable b2 is the only statistically significant coefficient
- both regression coefficients are statistically significant
