Question

Question 1 You are interested in studying the effect of the US minimum Rico. Therefore you use the following dataset wage on employment in Puerto Variable LPREPOP Log of the Puerto Rican employment per capita LMINCOVLog of the minimum wage relative to average wages Description time trend (1 to 38) LUSGNP Log of US gross national product a) Explain what autocorrelation is. Provide an example which illustrates the regression problem, and describe a method that can be used to reduce the impact of autocorrela- tion mar b) Consider the following two outputs at the bottom of this page and the top of the next i) How do you interpret the coefficient estimates in both outputs? Be as precise as ii) Explain the differences between the coefficient estimates for LUSGNP in Output iii) Test the nll hypothesis, that the coefficient in front of LMINCOV in Output 2 one: you can! 1 and Output 2. Give an economic interpretation equals-0.13. (Use a significance level of 5%) 10 marks Figure 1: Regression Output 1 Source 38 34.04 0.0000 0.6605 0.6411 .0557 df MS Number of obs F(2, 35) Model.211258194 108600157 2 .105629097Prob>F 35 .003102862 R-squarecd Residual Adj R-squared Total 319858351 37 .00864482Root MSE lprepop Coef. Std. Err p>It! [95% Conf. Interval] mincov1544433 .0649015 -2.38 0.023 .2862003 -.0226863 -.1918817.1675019 4994453 usgnp .0121899 .0885134 -0.14 0.891 cons 1.054413 .7654066 1.38 0.177 -2.608271Figure 2: Regression Output2 Source df MS umber of obs F(3, 34) 38 62.78 0.0000 0.847 0.8336 03793 Model.270947898 Residu.048910453 3 .090315966 Prob > F 34 .001438543 -squared Adj R-squared Iotal.319858351 37 .00864482 Root MSE lprepop Coef. Std. Err Pit! [95% Conf. Interval] minco.1686946 0442464 -3.8 0.001.2586142 .078775 69837761.416321 t0323541 .00502286.44 0.000 .0425616 -.0221467 consi -e·696267 1.295773-6.71 0.000-11.32962-6.06296 usgnp1.057349 .1766381 .99 0.000 e) Your colleague gives you a residual plot of the estimation shown in Output 2: Figure 3: Residual Plot 8 1950 1960 1970 1980 1990 What can you conclude from the residual plot and why? 4 marks (continued overleaf)d) You are carrying out the Breusch-Godfrey test which gives you the following output: Figure 4: Breusch-Godfrey regression output Source sS df 37 3.27 0.0236 32 .000919832 R-suared 0.2899 Adj R-squared0.2011 03033 MS Number of obs (4, 32) Model.012014608 Residual029434629 4 .003003652 Prob > F Iotal.041449237 36 .001151368 Root MSE ehat Coef. Std. Err t 即it! [95% Conf. Interval] mincov0306673 .0362028 0.85 0.403 -,0430753 lusgnp 10441 2684799 3233348 t001502 00417370.36 0.721 .0100035 .0069996 .0274274 145271 0.19 0.851 -, ehat Ll 478895 .1429749 3.35 0.002 18766467701253 cons-.1439263 1.062387 -0.14 0.893 -2.307939 2.020086 i) What are the null and alternative hypotheses? ii) What is the dependent variable in this output? ii) Calculate the test statistic. iv) Find the 5% critical value. v) Do you reject the hypothesis? vi) Do you revise your answers in question a) in the light of these test results? Why? Why not? 12 marks e) In order to take into account the dynamic properties of the error term, you decide to model it as an AR(1) or an MA (1) process. i) The Durbin-Watson statistic is equal to 0.339627. Can you conclude from the Durbin-Watson Statistic which process you should use? Why? Why not? i) Could the Breusch-Godfrey test help you with your decision which process youu should use? Why? Why not? 5 marks f) You decide to investigate the womans labor force participation in the Puerto Rican job market. As such you create a variable called JOB defined as: JOB1 if the it* Puerto Rican woman participates in the labor foree 0 otherwise i) What are the problems f you simply estimate a linear regression model using OLS, when the dependent variable is a dummy? 6 marks ii) Describe a model you could use to overcome these problems. 5 marks (Total: 50 marks)

0 0
Add a comment Improve this question Transcribed image text
Answer #1

Date: ----09/01/2019 swer. aAutocorrelation : It is Characteristic of data which shows the degree of similarity between the v

In Regression Output 2, We can say that, If Minimum Wage relative to average Wages increased by one Unit then Puerto Rican employment per Capita will decreases by 0.1686946. Also, One Unit increase in US Gross national Product will cause increase in Puerto Rican employment per Capita by 1.57349. When Minimum Wage and US Gross national Product are zero then Puerto Rican employment per capita is 8.696287 i As Interpret above, in Output 1 Unit increase in LUSGNP causes decrease in PREPOP by 0.121899 and in Output 2, decrease is 1.57349. We can say that, In Second Regression model, PREPOP is more sensitive to LUSGNP as compared to First. Economically US national Product plays big roll in deciding Puerto Rican employment per Capita in Second Model as compared to First i In order to test null hypothesis, Test Statistics is, se(B) -0.130.168696 0.0442464 -0.87456 Which follows T Distribution with 36 degrees of freedonm Conclusion: Here Calculated value (0.87456) < Table Value (2.3391). Therefore we are failed to reject null Hypotheses

C) Here residual exhibit fairly random Pattern. This Random Pattern indicates that a linear model provides a decent fit to the data. But still, If you observe closely, Residual values from 1950 to 1965 are smaller than that of 1965 to 1980, which suggest some kind of Pattern is present in Data, We need to check for Autocorrelation with other measures. d) Null Hypothesis: There is no serial Correlation (Autocorrelation) of any order upto p Alternative Hypothesis: At least one variable exhibit Serial Correlation (Autocorrelation) iii) Test Statistic for BG Test is, 37*0.2899 ..Test Statistics 10.7263 iv)Since Test statistics follows chi square distribution, Critical value is 9.34*8 v) Since, Calculated Value(10.7263)>Critical Value, We Reject Null Hypothesis

Add a comment
Know the answer?
Add Answer to:
Question 1 You are interested in studying the effect of the US minimum Rico. Therefore you...
Your Answer:

Post as a guest

Your Name:

What's your source?

Earn Coins

Coins can be redeemed for fabulous gifts.

Not the answer you're looking for? Ask your own homework help question. Our experts will answer your question WITHIN MINUTES for Free.
Similar Homework Help Questions
  • What does the coefficient estimate for lnNumHH tell you? Do you think there is a problem...

    What does the coefficient estimate for lnNumHH tell you? Do you think there is a problem with the regression, if so what is the problem? • regress lnMedInc in NumHH Source SS df MS Model Residual 1.92343603 8.48203352 1 364 1.92343603 02330229 Number of obs F(1, 364) Prob > F. R-squared Adj R-squared Root MSE IL L LLLL 366 82.54 0.0000 0.1848 0.1826 . 15265 Total 10.4054695 365 .028508136 InMedInc Coef. Std. Err. t P> [t] [95% Conf. Interval] InNumHH...

  • Given the following regression output in Stata Indicate what is the effect of x2 on Y...

    Given the following regression output in Stata Indicate what is the effect of x2 on Y by testing the hypothesis that x2 determines Y given · regress y xl x2 Source SS dEMS Model Residual 2.6644e+092 1.3322e+09 26878436.6 12 2239869.72 Number of obs = F( 2, 12) = Prob > F R-squared Adj R-squared = Root MSE 15 594.76 0.0000 0.9900 0.9883 1496.6 Total 2.6912e+0914 2.6912 192231167 Coef. Std. Err. t >It (95% Conf. Intervall x1 2.44061 .3440342 -32137.37 6.125326...

  • This question refers to the question 1 in Exam 1 e sleep and totwork (total work) is measured in ...

    This question refers to the question 1 in Exam 1 e sleep and totwork (total work) is measured in minutes per week and educ and age aremeasured in years, male is a dummy variable (male- 1 if the individual is male, and o if female) This is the STATA output of the model: 706 19.59 0.0000 0.1228 Adj R-squared0.1165 df MS Number of obs Model Residual 17092058.5 122147777 F (5, 700) 5 3418411.71 Prob>F 700 174496.825 R-squared Total 139239836 705...

  • In the solution proposal DF = 21 when testing this hypotheses, but when doing a f test for significant regression DF is 24. I need help understanding this:) Regards Richard df MS Source I Number of o...

    In the solution proposal DF = 21 when testing this hypotheses, but when doing a f test for significant regression DF is 24. I need help understanding this:) Regards Richard df MS Source I Number of obs 27 2. 24) - 200.25 - 0.0000 О. 9435 Adj R-squared 0.9388 .18837 2 7.10578187 Residual! .85163374 24.035484739 Model 14.2115637 Prob F R-squared Total 15.0631975 26.57935375 Root MSE Coef. Std. Err. [95% Conf. Interval] 125954 085346 .326782 1nLI.6029994 1nK I.3757102 cons1.170644 2.790.000 4.40...

  • A researcher is examining the effect of number of years in a particular job (tenure) on...

    A researcher is examining the effect of number of years in a particular job (tenure) on the hourly wage (USD) earned. She estimates two regression models using data on 124 young women surveyed in 1988. In the first regression, she regressed logged hourly wage on logged tenure in the current job (years in current job). In the second regression she regressed logged hourly wage on logged tenure in the current job, as well as age, total years of schooling completed,...

  • Question 1 First run the regression: EARNINGSi = β1 + β2ASVABCi + β3Si + ui Then...

    Question 1 First run the regression: EARNINGSi = β1 + β2ASVABCi + β3Si + ui Then run the regression with experience: EARNINGSi = β1 + β2ASVABCi + β3Si + β4EXPi + ui Compare the results from these two regressions, do you get an indication that the previous estimate of schooling without EXP was biased? If so, in which direction? And why is that? Question 2 Add gender dummy variable to the regression (the one running regression of EARNINGS on ASVABC,...

  • You are interested in analyzing whether pollution affects productivity at call centers. You have a dataset...

    You are interested in analyzing whether pollution affects productivity at call centers. You have a dataset that lists daily calls per worker made from call centers in different cities. The data also shows the Air Quality Index at the city on that date. The Air Quality Index is a measure of the number of particles in the air that ranges from 0 to 500. Lower levels indicate less pollution. The following lines are an extract from the full dataset date...

  • A researcher is examining the effect of number of years in a particular job (tenure) on...

    A researcher is examining the effect of number of years in a particular job (tenure) on the hourly wage (USD) earned. She estimates two regression models using data on 124 young women surveyed in 1988. In the first regression, she regressed logged hourly wage on logged tenure in the current job (years in current job). In the second regression she regressed logged hourly wage on logged tenure in the current job, as well as age, total years of schooling completed,...

  • Based on the multiple regression model, does demand for beef respond significantly to price of pork?...

    Based on the multiple regression model, does demand for beef respond significantly to price of pork? Why? df MS - - - - Source SS -----------+------- Model | 235.766738 Residual 57.3509099 ----------- ------- Total L 293.117648 3 13 78.5889127 4.41160845 Number of obs = EU3, 13) = Prob>F = R-squared = Adj R-squared = Root MSE = 17 17.81 0.0001 0.8043 0.7592 2.1004 - - - - - - - - - - - 16 18.319853 - - - -...

  • Model 1: You are undecided about whether to include education (educ) and gender (male) as controls....

    Model 1: You are undecided about whether to include education (educ) and gender (male) as controls. The output from a regression where you exclude education and gender is shown below: MODEL 2: affair бо + 6,relig = reg affair relig df SS MS Number of obs 601 Source F (1, 599) 10.31 Model Residual| Prob > F 0.0014 1.90494147 1.90494147 599 0.0169 110.657455 184736986 R-squared Adj R-squared 0.0153 = Total 112.562396 600 .187603993 .42981 Root MSE Interval] affair Coef Std....

ADVERTISEMENT
Free Homework Help App
Download From Google Play
Scan Your Homework
to Get Instant Free Answers
Need Online Homework Help?
Ask a Question
Get Answers For Free
Most questions answered within 3 hours.
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT