ETF3200-ETF5200 Applied Econometrics Tutorial 1
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
ECONOMETRICS AND BUSINESS STATISTICS
Applied Econometrics
Tutorial 1
1. Describe the assumptions of the classical linear regression model. What are the implications for the properties of the OLS estimator if each one of these assumptions is violated?
2. Let the following linear model given by yi = Fxi + ei , i = 1, …, N. Two estimators b1 and b2 of F are defined by
b1 = ∑yi ⁄∑ xi and b2 = ∑yi xi ⁄∑x i(2) .
Show that
a. both b1 and b2 are unbiased estimators of F (if we assume that E(ei ) = 0 )
b. the variance of b1 is greater than that of b2 (if we treat the xi as given, rather than random). Why should you expect this?
3. Page 133, Ex. 3.1.
4. Practice on EViews:
a. Use thefood.wfl dataset to estimate a simple regression of food expenditure on income. Define the marginal propensity to spend income on food, and then use your output to estimate this propensity. Then define the elasticity of food consumption with respect to income, and estimate this elasticity at the sample means. Interpret the coefficient in economic terms: what can you conclude from the analysis?
b. Use the br.wfl dataset to provide a scatter plot of price vs square feet, and comment on whether you think that a linear model (of price regressed on house size in square feet) might be appropriate for this data, providing some rationale for your answer.
c. Use the same data set as in b. to estimate a quadratic model of house prices as a function on the squared values of house size. Define and interpret the marginal effect of the independent variable. What can you conclude from the analysis?
d. Use the same dataset as in b. to estimate a log-linear model. Define and interpret the marginal effect of the independent variable: did your conclusion change from part c? Why?
2022-09-01