ECOM20001 Intro Econometrics assignment 代写

  • 100%原创包过,高质代写&免费提供Turnitin报告--24小时客服QQ&微信:120591129
  • ECOM20001  Intro Econometrics assignment 代写


    ECOM20001  Intro Econometrics 



    ECOM20001  Intro Econometrics  Semester 1, 2017
    1/3
    Assignment 1  Due Friday April 28 th 1:00PM.
    This assignment is evaluated for a total of 30 marks. It is worth 10% of your final mark. No late
    assignments will be accepted. Please submit it electronically using from LMS. This is an individual
    project each person is expected to do their own assignment. It is due by 1pm on Friday the 28 th of April.
    Make sure to use the table below to record your name and student id, your tutor’s name and tutorial
    time/location.
    This assignment has two parts the first is worth 10 marks and the second is worth 20. The first is
    a question taken from last year’s final examination. The second requires that you use the data
    (UN_HDI.wf1)for the assignment to perform some estimation and interpretation.
    Please limit your total response to no more than 10 A4 pages. You may cut and paste the Eviews
    output in your file. In most cases any figures will probably need to be reduced in size. Make sure to
    keep a copy of what you submit and include your full name, ID number, your tutor’s name, the
    time/day/location of your tutorial as shown below:
    Name ID number  Tutor  Tutorial day &
    time
    Tutorial
    location
    ECOM20001  Intro Econometrics  Semester 1, 2017
    2/3
    1.  Question from last year’s exam (10 marks total)
    Show all your workings in answering these questions.
    1.  Two specifications of an equation that explains the expenditures per adult on EGMs (pokies) for
    the fiscal year 2012/2013 (exp_per_adult) in terms of the number of EGMs per 1000 adults in 2013
    (EGM) and the unemployment rate (unemployed) for a sample of 70 towns in Victoria, Australia were
    estimated. The results are reported in Table 1 with standard errors in parentheses.
    Table 1 The estimated parameters and standard errors for the two specifications
    ExplanatoryVariables  Specification 1: Specification 2:
    Constant  -108.06 (67.527)  -218.83 (75.725)
    EGM  44.87 (7.430)  99.71 (20.972)
    EGM 2 -3.71 (1.334)
    unemployed  56.98 (10.677)  45.36 (11.004)
    2
    R
    0.542  0.583
    Questions:
    1.a.(2 marks) Discuss which specification you prefer. In your discussion you must use the
    results of at least two criteria.
    1.b(2 marks) Estimate the expenditures per capita of 200 EGM per 100 people on the predicted
    exp_per_adult for specification 1.
    1.c(2 marks) Estimate the expenditures per capita of 200 EGM per 100 people on the predicted
    exp_per_adult for specification 2.
    1.d. (2 marks)  From specification 2, what can we conclude about the returns to scale of more
    EGMs?
    1.e. (2 marks)  From specification 2, how many EGMs per capita would there have to be in a town
    to have negative returns to scale?
    ECOM20001  Intro Econometrics  Semester 1, 2017
    3/3
    2.  The Productive and Fair Econometrician (20 marks total)
    Recently the United Nation Development Programme released their latest Human Development
    Report. 1 In this assignment you are asked to run some regressions to determine the influence of various
    measures of human development such as measures of education and health, inequality and economic
    activity to examine the relationship between some of these measures. In order to perform this analysis a
    selection of data from the World Bank was combined with the UN data is contained in UN_HDI.wf1. 2
    Table 2. Descriptive statistics for variables in UN_HDI.wf1
    mnemonic  Description  Mean  Max  Min  SD.  Obs
    ARTICLES  Scientific articles per 1000 population  6.588  49.480  0.016  10.85  134
    CO2  Carbon dioxide emissions per capita, (tonnes), 2011  4.684  43.893  0.022  6.293  187
    EN_SEC  Secondary enrolment, (% of sec school–age population), 2008–2014  79.9  135.5  15.9  26.6  178
    EN_TER  Tertiary enrolment, (% of ter school–age population), 2008–2014  36.07  116.62  0.81  27.35  167
    EQ_MATH  Performance of 15-year-old students, Mathematics, 2012  471  613  368  55  63
    EQ_READING  Performance of 15-year-old students, Reading, 2012  473  570  384  47  63
    EQ_SCIENCE  Performance of 15-year-old students, Science, 2012  477  580  373  51  63
    EQ_SEC  Population with some secondary education, (% ages 25 and older)  57  100  2  29  156
    FER_2010  Total fertility rate, (births per woman),2010/2015  2.875  7.580  1.130  1.418  183
    GDP_CAP  Gross domestic product (GDP)Per capita (2011 PPP $), 2013  17005  127562  584  18867  183
    GR_HDI  Average annual HDI growth, (%), 1990–2014  0.811  2.889  -0.041  0.511  143
    HDI  Rank of Human Development Index 2013  94  188  1  54  188
    HDI_VALUE  Human Development Index, Value, 2014  0.692  0.944  0.348  0.155  188
    IMMIGRANTS  Stock of immigrants as a % of population, 2013  9.039  83.746  0.060  13.426  188
    INEQ_GINI  Income inequality, Gini coefficient, 2005–2013  39.16  65.77  24.82  9.16  142
    INEQ_PALMA  Income inequality, Palma ratio2005–2013  2.070  7.979  0.849  1.317  142
    INEQ_QUIN  Income inequality, Quintile ratio, 2005–2013  8.569  40.239  3.445  5.626  142
    INTERNET  Communication, Internet users, (% of population), 2014  44.207  98.160  0.990  29.104  185
    LIFE_EXP  Life expectancy at birth  62.184  76.045  41.452  8.191  134
    MED_AGE  Population, Median age, (years), 2015  28.757  46.543  14.957  8.680  183
    MORT_INF  Mortality rates, (per 1,000 live births), Infant, 2013  25.5  107.2  1.6  23.7  186
    POP  Population, Total, (millions), 2014  38.2  1393.8  0.0  141.7  188
    POP_URBAN  Population, Urban, (%), 2014  56.6  100.0  11.8  23.2  183
    PRIS_POP  Prison population, (per 100,000 people), 2002–2013  168  716  16  132  185
    PRODUCTIVITY  Labour productivity, Output per worker, (2011 PPP $), 2005-2012  33500  149978  1675  28440  135
    R_N_D  Research and development expenditure(% of GDP), 2005–2012  0.915  4.039  0.013  0.975  116
    TOURISTS  Human mobility, International inbound tourists, (thousands), 2013  5709  84700  0  12002  187
    WOMEN_MPS  % of seats in parliament held by women, 2014  20.624  57.547  0.000  11.601  185
    In answering this question do not try to fit numerous alternative models. Estimate only a few and
    answer the question. In some cases there are no single “right” answers – you are evaluated on your
    interpretation of what you find.
    Just as in the case of real applications (this is actual data), not all variables have the same number
    of observations. Some countries do not have data for all variables as noted in the Obs column in Table 2.
    When EViews runs a regression it is based on the countries (observations) for which all the variables are
    non-missing, thus you should check this when using different variables when the numbers of observations
    vary. 
    1 See http://hdr.undp.org/en/2016-report for details.
    2 See http://data.worldbank.org/ for details.
    ECOM20001  Intro Econometrics  Semester 1, 2017
    4/3
    Questions to be answered using the UN_HDI.wf1 data set. (20 marks in total)
    2.a. (1 mark) The Kuznets Curve is a widely cited relationship between income and inequality. Whereby it
    is hypothesised that as income increases inequality increases up to a point but after that point
    the inequality decreases with higher income, thus higher income countries have lower
    inequality than lower income countries. This phenomenon implies that the function between
    inequality (as dependent variable) and the log of income (as independent variable) will
    exhibit an inverted U-shape. Using the log of the measure of income (GDP_CAP) examine
    the relationship between the three measures of inequality (INEQ_GINI, INEQ_QUIN,
    INEQ_PALMA)  3 in this data series using scatter plots.
    2.b (1 mark) What can you conclude about the existence of the existence of the Kuznets Curve from the
    plots you generated in part 2.a?
    2.c (3 marks) Follow up the descriptive analysis you performed in 2.a and 2.b with the estimation of three
    regressions where you allow for the inverted U-shaped relationship with a quadratic
    specification in the log of GDP_Cap. 4
    2.d (3 marks)  From these regressions locate a limiting value of the income where the relationship between
    inequality and income reverses as Kuznets proposed.
    2.e (2 mark)  Is this “turning point” the same for the three different measures of inequality? Propose
    reasons why would these turning points might differ between the models?
    2.f (1 mark) Labour productivity is considered an important measure of the health of an economy.
    Recently, the impacts of immigration to different countries have become a hot issue for
    political debate. Estimate a model of the log of labour productivity as measured by the log of
    output per worker (PRODUCTIVITY) variable with the % of the population that are
    immigrants (IMMIGRANTS), the % of tertiary aged people enrolled in tertiary institutions
    (EN_TER) and the % of the population that live in urban areas (POP_URBAN) as the
    explanatory variables.

    ECOM20001  Intro Econometrics assignment 代写
    2.g (3 marks)  Interpret these parameter estimates found in part 2.f and draw conclusions as to the impact of
    these regressors in explaining productivity.
    2.h (1 mark)  Using the number of scholarly articles per capita (ARTICLES), as a measure of a society’s
    education and the capacity for non-subsistence effort, estimate a model with this measure as
    the dependent variable and the % of tertiary aged people who are attending tertiary
    institutions (EN_TER), the % of the population that have access to the internet
    (INTERNET), and a social measure such as the % of members of parliament that are women
    (WOMEN_MPS).
    2.i (5 marks)  Interpret your findings and establish if these variables influence the number of articles only
    in a monotonic way. In addition, suggest one or two alternative regressors that could be
    included in this model. (don’t attempt to use more than 5 other variables). Make sure to
    provide reasons as to why they could be used.
    3 You can find definitions of these measures on line.
    4 Note that a typical quadratic regression of x on y would be specified in EViews as y x x^2 c for the regression
    2
    1 2 3
    y x x    .

    ECOM20001  Intro Econometrics assignment 代写