You are given the following linear regression: log(S_i) = beta\'_0 + beta\'_1 T_

Question

You are given the following linear regression: log(S_i) = beta'_0 + beta'_1 T_i + beta'_2 log(E_i) + beta'_3 log(P_i) + beta'_4 log(H_i) + u'_i You run the model and you obtain the following output: Dependent Variable: LOG(S) Method: Least Squares Included observations: 38 1. The F value you obtained is missing. Calculate it and test it for 5% significance level. The F critical is given as 2.65. 2. We do not know which model is better performed. Make use of the Coefficient of Variation and find out which model is better.

Explanation / Answer

(1.)

The formula F=[R2*(n-k-1)]/[(1-R2)*k] can be used here.

Here, R2 is given as 0.866335

n is the total number of observations i.e 38

k is the number of independent variables excluding the constant term i.e 4

So the value it gives is F=53.47146785 which is still greater than the critical value i.e 2.65 so we reject the null hypothesis.

Conclusion:

Since, F-statistic>F-critical(53.47146785>2.65), there is significant evidence to beleive that the test is significant.

So, we reject the null hypothesis

(2.) The other models are not specified to calculate the coeeficient of variation.

We can thus only calculate the coeeficient of variation of the given model.

The formula for coefficient of variation is C.V =100* (/µ^)

the value are given for the dependent variable

µ=2.083406

=0.325515

Putting the value in the formula we get C.V =100*0.15624175

C.V =15.624175

Related Questions

Navigate

• Browse (All)
• Browse Y
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.