In: Statistics and Probability
We give JMP output of regression analysis. Above output we give the regression model and the number of observations, n, used to perform the regression analysis under consideration. Using the model, sample size n, and output:
Model: y = β0+
β1x1+
β2x2+
β3x3+
ε Sample size:
n = 30
Summary of Fit | |
RSquare | 0.956255 |
RSquare Adj | 0.951207 |
Root Mean Square Error | 0.240340 |
Mean of Response | 8.382667 |
Observations (or Sum Wgts) | 30 |
Analysis of Variance | ||||
Source | df | Sum of Squares |
Mean Square |
F Ratio |
Model | 3 | 32.829545 | 10.94320 | 189.4492 |
Error | 26 | 1.501842 | 0.05780 | Prob > F |
C. Total | 29 |
34.331387 |
Total variation (2) Report R2 and R¯¯¯2 as shown on the output. (Round your
answers to 4 decimal places.) (3) Report SSE, s2, and s as shown on the output. (Round your
answers to 4 decimal places.) (4) Calculate the F(model) statistic by using the explained
variation, the unexplained variation, and other relevant
quantities. (Round your answer to 2 decimal places.) (6) Find the p−value related to F(model) on the output. Using the p−value, test the significance of the linear regression model by setting α = .10, .05, .01, and .001. What do you conclude? p-value =.0000. Since this p-value is less than α =.001, we
have evidence |
<.0001* |
(1) Report the total variation, unexplained variation, and explained variation as shown on the output. (Round your answers to 4 decimal places.)
Total variation:100%
unexplained variation:95.63%
explained variation:100-95.63=4.37%
2) Report R2 and R¯¯¯2 as shown on the output. (Round your
answers to 4 decimal places.)
R^2=0.9563
-
R2=0.9512
3) Report SSE, s2, and s as shown on the output. (Round your
answers to 4 decimal places.)
SSE=1.5018
S^2=MSE=0.0578
s=sqrt(MSE)=0.2404
(4) Calculate the F(model) statistic by using the explained
variation, the unexplained variation, and other relevant
quantities. (Round your answer to 2 decimal places.)
F(model)=MS Square Error/MS Model=10.94320.05780=189.45
6) Find the p−value related to F(model) on the output. Using the p−value, test the significance of the linear regression model by setting α = .10, .05, .01, and .001.
p-value =.0000. Since this p-value is less than α =0.1, we
have evidence
that H0: β1 = β2 = β3 =0 is false. That is, we have
evidence
that at least one of x1, x2 ,and x3is significantly related to
y.
p-value =.0000. Since this p-value is less than α =0.05, we
have evidence
that H0: β1 = β2 = β3 =0 is false. That is, we have
evidence
that at least one of x1, x2 ,and x3is significantly related to
y.
p-value =.0000. Since this p-value is less than α =0.01, we
have evidence
that H0: β1 = β2 = β3 =0 is false. That is, we have
evidence
that at least one of x1, x2 ,and x3is significantly related to
y.
p-value =.0000. Since this p-value is less than α =0.001, we
have evidence
that H0: β1 = β2 = β3 =0 is false. That is, we have
evidence
that at least one of x1, x2 ,and x3is significantly related to
y.