|There will be a second attachment that has the data to use for the coursework, you will need to have the program eViews already downloaded to be able to open it.|
|Order Topic:||Data Analysis .. using the program eViews|
Download the program eViews .. as this coursework requires you to use this program to complete the coursework (there are 2 versions of this program, one of them is free and can be used to do this work as we don”t need more than 1500 observations.
UNIVERSITY OF WESTMINSTER WESTMINSTER BUSINESS SCHOOL 4EQM7C1 DATA ANALYSIS Coursework Semester 1 2016/17 Submission Instructions 1. Only an electronic copy should be handed-in via the blackboard site of the module by 1:00 p.m. (13:00) UK time on 24 NOVEMBER 2016. This copy will automatically be scanned through a text matching system (designed to check for possible plagiarism and collusion). 2. To avoid mark penalisation for late submission ensure you submit your coursework in time according to the deadline above. See module handbook (Section 9) for details on mark penalisation for late submission and step by step on-line submission instructions. 3. The name and the registration number of the student should be clearly shown on the Örst page of the assignment. General Instructions 1. This coursework is INDIVIDUAL. 2. Provide and explain all calculations and relevant EViews outputs. 3. Use a signiÖcance level of 5% for all tests. 4. Presentation is worth 10% of the total coursework marks ónote that a good presentation requires clear and concise answers avoiding redundant information. 5. Word limit: 3,000.1 6. The coursework is worth 30% of the total module mark. A qualifying mark of a minimum of 35% is required in this piece of assessment to pass the module. 1Appendices and footnotes do not count for the word limit. If necessary 1) put tables (Eviews outputs) in an appendix and refer to them in the bodydtext of the paper, and 2) use footnotes for secondary information in your answers. 1 Questions The EViews Öle “DataCWSM1_1617.wf1” (available from Blackboard/Assessment) provides a data set of 1,499 college students. The description of the variables in the Öle is given below: COLGPA = college performance (in points) HSPERC = percentile in the high school graduating class (deÖned so that, for example, HSPERC=5 means the top 5% of the class) HSIZE = size of the graduating class (in hundreds) SAT = combined maths and verbal score on the student achievement test (in points) FEMALE = gender dummy variable equal to one for female students ETHASIAN = dummy variable equal to one if ethnic group asian ETHBLACK = dummy variable equal to one if ethnic group black ETHWHITE = dummy variable equal to one if ethnic group white ATHLETE = dummy variable equal to one for student-athletes Using this data set answer all following questions: Q1. Regress the variable COLGPA on the variables HSPERC, HSIZE, SAT, FEMALE, ETHASIAN, ETHBLACK, ATHLETE ónote that a constant should be included in the model (denote it as !1). Provide the multiple linear regression model speciÖcation including the independent variables in the same order as they are presented in the table above. [8 marks] (a) Provide an interpretation to the coe¢cient estimates of that regression. Why does it make sense for the coe¢cient of HSPERC to be negative? What is the meaning of the estimated intercept in this equation? (b) Perform tests for the statistical signiÖcance of the parameters of the independent variables HSIZE and SAT using the critical value of the corresponding tdistribution and the test p-value. Interpret the tests results. 2 ALL questions below refer to the regression in Q1: Q2. Perform a joint signiÖcance test for the independent variables of the model using both the p-value and the critical value of the F-distribution. [4 marks] (a) Comment on the goodness-of-Öt of the model. What other factors might a§ect COLGPA? (b) What are the consequences of the results of this F-test together with those of the t-tests (from question 1) for the speciÖcation of the model? Q3. Test the hypothesis: 5 extra points in SAT has the same e§ect as 100 fewer students in class, on COLGPA. [8 marks] (a) Use the command available in EViews to test for the corresponding coe¢cient restriction. (b) Perform the test analytically. (c) Interpret the test results. Q4. Answer the subquestions below on multicollinearity. [8 marks] (a) Test for multicollinearity between the independent variables HSPERC and HSIZE in the model. Explain your answer using EViews outputs. (b) Assuming that there is multicollinearity between those variables: i. Explain how you would resolve this problem. Explain your answer using EViews outputs. ii. What are the consequences of multicollinearity for the OLS estimator? Q5. Answer all two parts. [4 marks] (a) Perform a graphical analysis to detect the presence of heteroscedasticity in the model using at least two di§erent plots. Do you Önd evidence of heteroscedasticity? Why? (b) Explain the consequences of heteroscedasticity on the OLS estimator. 3 Q6. Perform a White test for heteroscedasticity. [6 marks] (a) Provide the auxiliary regression and explain the meaning of the null hypothesis for this test. (b) Why is the White test preferred to the Breusch-Pagan and Goldfeld-Quandt tests for heteroscedasticity. Explain your answer. Q7. Assume that there is heteroscedasticity of the form: “2 ui = “2 u ! HSIZE 1 3 i : How would you resolve the problem of heteroscedasticity in this case? Explain your answer analytically. [4 marks] Q8. Answer all two parts. [4 marks] (a) Estimate the model using White heteroscedasticity-consistent standard errors. Comment on the results of that estimation in relation to the estimation results in question 1. (b) When do we use White standard errors? Q9. Answer all two parts. [4 marks] (a) Provide a graphical analysis of the residuals to detect the presence of autocorrelation using at least two di§erent plots. Do you Önd evidence of autocorrelation? Why? (b) What are the consequences of autocorrelation on the OLS estimator? Q10. Test for autocorrelation in the residuals using an appropriate procedure. [4 marks] Q11. All other factors being equal, is there evidence on that the ethnic group has an e§ect on college performance? How strong is the evidence? Show all steps of the corresponding test to answer this question. [6 marks] Q12. Test whether SAT results have a di§erent e§ect on college performance for females and males? Show all steps of the corresponding test to answer this question. [6 marks] Q13. Are COLGPA functions di§erent for student-athletes and student-non-athletes? Explain in detail all steps involved in the implementation of the test your perform to answer this question [8 marks] 4 Q14. Describe step by step how you could test for the best functional form for the model in Q1. [6 marks] Q15. Test the assumption of normality in the residuals of the model in Q1 by using the Jarque-Bera (JB) test. Comment on the implications of your JB test results on the properties of the OLS estimator. [4 marks] Q16. For what purpose your analysis above could be used by the Ministry of Education? Explain your answer. [6 marks] [End of coursework]
Save your time - order a paper!
Get your paper written from scratch within the tight deadline. Our service is a reliable solution to all your troubles. Place an order on any task and we will take care of it. You won’t have to worry about the quality and deadlinesOrder Paper Now