Reference no: EM132417946
Problem: A multiple regression model, R=a+bw+cX+dZ, is estimated by a computer package, which produces the following output:
DEPENDENT VARIABLE: R R-SQUARE F-RATIO P-VALUE ON F
OBSERVATIONS: 34 0.3179 4.660 0.00865
PARAMETER STANDARD
VARIABLE ESTIMATE ERROR T - RATIO P-VALUE
INTERCEPT 12.6 8.34 1.51 0.1413
W 22.0 3.61 6.09 0.0001
X -4.1 1.65 -2.48 0.0188
Z 16.3 4.45 3.66 0.0010
Required:
Question 1: How many degrees of freedom does this regression analysis have?
Question 2: What is the critical value of t at the 2 percent level of significance?
Question 3: Test to see if the estimates of a,b,c, and d are statiscally signifcant at the 2 percent significance level. What are the exact levels of significance for each of the parameter estimates?
Question 4: How much of the total variation in R is explained by this regression equation? How much of the total variation in R is unexplained?
Question 5: What is the critical value of the f-statistic at the 1 percent level of significance? Is the overall regression equation statistically significant at the 1 percent level of significance? What is the exact level of significance for the F-statistic?
Question 6: If W equals 10, X equals 5, and Z equals 30, what value do you predict r will take? If W, X, and Z are all equal to 0?