ECMT 5001 ear 2008 Semester 2_ECMT 5001 Solution Tutorial 7.docVIP

Econometrics Business Statistics ECMT5001: Principles of Econometrics Tutorial 7: Inference in Simple Linear Regression - Solutions (Gujarati, Ex. 6.4) Consider the following regression results Fill in the two gaps in parentheses. For B1: For B2: For H0: B2=0, . So, and . For B2: Note: One way to think of it, computer output. Variable Coefficient SE(b) t P-value Intercept b1 SE(b1) X1 b2 SE(b2) Test the hypothesis against a two-sided alternative at the 5% level of significance. H0: B2=0 vs. H1: B2 ≠0. Level of Significance: α = 0.05 Hypothesis tests for regression coefficients are always t-tests. Distribution: assuming that the error is distributed iidN(0,) and all other assumptions are met. Rejection rule: Reject H0 if tobs2.101 or tobs-2.101. Calculated Value: t* = 18.73 Conclusion: Since t* =18.732.101, we reject H0 at the 5% level. Conclude that the evidence is sufficient to support the hypothesis that the slope coefficient is not equal to zero at the 5% level of significance. Based on a sample of 25 observations, the population regression model was estimated. The least squares estimates obtained were b1 = 5 and b2 = 1.5, with TSS = SYY = 256 and RSS = 175. Compute the estimates of the standard errors for b1 and b2. Test the hypothesis that population slope parameter is zero against the two-sided alternative using a 5% significance level. H0: B2 = 0 HA: B2 ≠ 0 Level of Significance: α = 0.05 Distribution: . Assuming that the ui ~ iid N(0,σ2) and assuming all other assumptions are met. Critical Value: The two tailed critical value at the 5% level is 2.069with 23 df Rejection Rule: Reject H0 if t* is greater than 2.069 or t* -2.069 Calculated Value: t* = 3.263 Conclusion: Since t* = 3.263 is less than 2.069, we reject the null hypothesis at the 5% level. Conclude that the evidence supports the hypothesis tha