ECON213-16S1 (C) Semester One 2016

Introduction to Econometrics

15 points

Details:
Start Date: Monday, 22 February 2016
End Date: Sunday, 26 June 2016
Withdrawal Dates
Last Day to withdraw from this course:
  • Without financial penalty (full fee refund): Sunday, 6 March 2016
  • Without academic penalty (including no fee refund): Sunday, 22 May 2016

Description

Simple and multiple regression, elementary time-series analysis, introduction to econometric modelling.

This course teaches basic skills in econometrics, which is the statistical analysis of economic data. The emphasis in this class is on doing! Over the course of the semester, you will learn how to (i) develop a regression model, (ii) estimate it, and (iii) interpret it. General topics that we will cover include OLS regression, prediction, dummy variables, model specification, model selection, robust standard errors, time series forecasting, endogeneity, and qualitative choice models (logit and probit). You will gain much hands-on experience estimating statistical models using the software package EViews.

Learning Outcomes

  • Learning Goals.  In this course you will learn how to:
  • Estimate relationships between variables using OLS regression
  • Interpret OLS regression output
  • Interpret coefficient estimates in linear regression models, including coefficients for dummy variables, interaction effects, and quadratic terms; in both linear, logged and semi-logged specifications
  • Test linear hypotheses about regression coefficients, and know how to interpret those tests
  • Use regression output to predict values of the dependent variable for given values of the explanatory variables
  • Use higher level modelling skills to develop, estimate, and analyse your own economic model
  • Understand (i) what serial correlation and heteroskedastity are, (ii) their consequences for OLS regression, and (iii) how to estimate “robust” standard errors
  • Recognize applications where endogeneity is likely to be a problem, and understand its consequences for OLS regression
  • Identify good instrumental variables and use 2SLS to correct for endogeneity bias
  • Critically analyse the results of 2SLS estimation to determine whether 2SLS represents an improvement over OLS
  • Develop univariate ARMA models for forecasting time series data
  • Understand the consequences of using OLS to estimate regression models with a binary dependent variable
  • Estimate logit and probit models, and know how to interpret and evaluate the output from estimating those models
  • Identify some common practical problems encountered in model estimation, and know how to address these problems
  • Become proficient in the use of EViews statistical software
  • Understand the theory underlying OLS and GLS estimation.
  • Mathematically derive the formulae for calculating OLS and GLS (i) regression coefficients and (ii) standard errors, using both summation operators and matrix calculus.

Prerequisites

(1) ECON104 or ECON105; and (2) 15 points from STAT or MSCI110. RP: MATH101 or Year 13 Math with Calculus.

Recommended Preparation

MATH101 or Year 13 Math with Calculus.

Course Coordinator

Bob Reed

Assessment

Assessment Due Date Percentage 
Weekly assignments 10%
Final Exam 35%
First term E-Views test 30 Mar 2016 25%
Second term E-Views test 01 Jun 2016 30%

Course links

Course Outline

Notes

You will need to hire an "electronic clicker".  These may be obtained from the Copy Centre (located in Fine Arts, Building 2).  The initial outlay for the clickers is $50, but all $50 will be refunded to you at the end of the semester when you return your clicker.  Note:  You will need to buy two AAA batteries for your clicker straightaway.

Indicative Fees

Domestic fee $759.00

International fee $3,125.00

* All fees are inclusive of NZ GST or any equivalent overseas tax, and do not include any programme level discount or additional course-related expenses.

For further information see Department of Economics and Finance .

All ECON213 Occurrences

  • ECON213-16S1 (C) Semester One 2016