ECON7310: Elements of Econometrics
Research Project 1
ECON7310代写 This is not a group assignment, which means that you must answer all the questions in your own words and submit…
Marking Allocation
Instruction ECON7310代写
This is not a group assignment, which means that you must answer all the questions in your own words and submit your report separately. To facilitate the grading work, please clearly label all your answers. upload your research report via the “Turnitin” submission link (in the folder of “Assessment”) by 11:00 on the due date 12 April, 2021. The marking system will check the similarity, and UQ’s student integrity and misconduct policy on plagiarism apply. Answer all questions following a similar format of the answers to your tutorial questions. That is, your empirical analysis has to based on the correct STATA outputs, and you should highlight the outputs in your answers.
Data Description
The data set Assign I Data.csv contains data collected from the real estate pages of the Australian. These are homes selling in the greater Brisbane area. In particular, you have the following variables: ECON7310代写
- id,house ID number;
- price,the selling price of the house in $1000;
- bdrms,the number of bedrooms;
- lotsize,the size of the lot in square feet;
- sqrft,the size of the house in square feet;
- colonial,a dummy variable which is equal to 1 if the home is colonial
Research Questions ECON7310代写
(a) (5 points) Obtain the summary statistics (i.e. mean, median, standard error, minimumand maximum, etc.) and histograms for the variables price and sqrft. Discuss the data Use a scatter plot and a regression line to explore the relationship between price and sqrft.
(b) (10points) Estimate the linear regression model1
pricei = β0 + β1 × sqrfti + ui (1)
Report the OLS estimation results in the standard form introduced in the lecture or text- book2. In addition, interpret the estimated intercept term, slope coefficient, and R2. ECON7310代写
(c) (10 points) Calculate the regression residuals and plot them against id and sqrft, respec- Do you think the exogeneity (E[ei sqrfti] = 0) and homoskedasticity (V [ei sqrfti] = σ2) assumptions are reasonable for the data? Explain. [Hint: If these two assumptions were valid, the scatter plots of residuals should show no evident patterns, i.e., we would expect the residual has zero mean (conditional and unconditional) and its conditional variance does not depend on the value of sqrft.]
(d) (10points) Estimate Model (1) using OLS but compute homoskedasticity-only standard errors (SE). Compare the regression results with what you obtained in (b). Comment your findings.
(e) (10points) The lot size (lotsize) and house style (colonial) may also affect the house Use a scatter plot to explore the relationship between price and ln(lotsize). Comment on your findings. How many houses in the sample are of colonial style? Are these houses on average more expensive than those non-colonial style houses in a significant way?
(f) (15points) Estimate the following multiple linear regression model ECON7310代写
pricei = θ0 + θ1 × sqrfti + θ2 × ln(lotsizei) + θ3 × coloniali + ui (2)
Report the estimated model and interpret the estimated coefficient on coloniali. Comment on the significance of the individual coefficient estimates. Do you prefer the regression model (2) to the regression model (1)? Explain.
(g) (10 points) Test the null hypothesis H0:θ2 = 31 (vs. H1: θ2 = 31) at the 1%, 5%, and 10% significance levels and construct the corresponding confidence intervals (CI). Re-do these tests with homoskedasticity-only Comment on your findings.
(h) (15points) Test the null hypothesis H0: θ2 = 31 and θ1 = θ3/10 at the 10% significance What is the alternative hypothesis H1 of this test? Test the null hypothesis H0: 10θ1 + θ3 = θ2 at the 5% significance level. What is the 95% CI for 10θ1 + θ3 − θ2?
(i) (10 points) Use Model (2) to predict the price of a non-colonial style house with sqrft =1, 500 and lotsize = 500. Find a 95% CI for your prediction. Do you think the 95% CI makes sense? Why? ECON7310代写
(j) (5points) The lecturer suggested to include the interaction term between sqrt colonial. If we can, how to interpret its coefficients? If we cannot, why?
