1. Consider the multiple regression model Y=XB u. Standard matrix notations apply. Derive OLS estimator for (3. Prove that B is Best Linear Unbiased Estimator (BLUE).

2. What is meant by stationarity in a time series? What are the implications of non-stationarity How do you test for stationarity in a time series?

3. Consider the following two-equation system:

<img src='./qimages/10370-3.jpg'>

Explain the identification condition of both the equations.

Explain how the first equation can be estimated.

4. Explain the underlying idea behind the linear probability model. What are its limitations? Explain how logit model takes care of these limitations.

5. What are the consequences if a data set has autocorrelation problem? Explain a method of testing for it.

6. Consider the production function

<img src='./qimages/10370-6.jpg'>

Derive OLS estimator for the parameters and interpret the model.

7. What is the difference between R2 and adjusted Interpret both the terms.

8. Explain the Granger causality test procedure for investigating whether xt causes Yt.

9. While estimating a regression model you found that the dependent variable is measured with certain error. Specify the model. What are its consequences on the parameters

10. Explain the concept of multicollinearity. What are its consequences? What are the measures taken to reduce the problem

11. Distinguish between fixed effects and random effects models in a panel data. Outline steps to estimate fixed effects model.

12. Write short notes on the following:

Error Correction Model

ARIMA Models