APPLIED TIME SERIES ECONOMETRICS (ECON 797W: Spring 2011, UMass Amherst)

APPLIED TIME SERIES ECONOMETRICS (ECON 797W: Spring 2011, UMass Amherst) Instructor Deepankar Basu Office: 1012 Thompson E-mail: dbasu@econs.umass.edu TA Charalampos Konstantinidis Office: 804 Thompson Hall E-mail: ckonstan@econs.umass.edu Classes: Monday 6:15-8:45pm in W-22 Machmer Instructor Office Hours: Tuesday 1:00-3:00pm, or by appointment TA Office Hours: TBA About the course: This course will introduce students to the basic techniques of time series econometric analysis and encourage them to apply some of these techniques to answer questions in heterodox macro/pe. The material that will be discussed in the course can be divided into two parts: (a) analysis of stationary time series processes (both univariate and vector processes), and (b) analysis of non-stationary time series processes (both univariate and vector processes). Textbook: The following textbook will be used to organize discussion of the material: Applied Econometric Time Series (Third Edition), by Walter Enders, 2010 [Publisher: John Wiley & Sons]. Supplementary Textbooks The following textbooks can be used for reference: Time Series Analysis, by James D. Hamilton, 1994 [Publisher: Princeton University Press] Econometrics, by Fumio Hayashi, 2000 [Publisher: Princeton University Press] Statistical Packages: We will work with two popular statistical packages in this course: R and STATA. The following links can be used to familiarize oneself with these packages for time series analysis: 1

For R: http://www.stat.pitt.edu/stoffer/tsa2/r\_time\_series\ _quick\_fix.htm For STATA: http://archive.nyu.edu/bitstream/2451/29569/2/ Brief\%20Introduction\%20to\%20Stata\%2010\%20Time\%20Analysis. pdf Grading: A total of 200 points will be divided between 5 take-home assignments and a research paper as follows: Take-home assignments: The 5 take-home assignments will be worth a total of 100 points, with each contributing 20 points. The assignments will be handed out in class and will be due in about 7-10 days; they will involve solving end-of-chapter problems, with every assignment (other than the first) including a data exercise. Data exercises can be completed using R or STATA. Details of tutorial sessions to help familiarize students with R and/or STATA will be announced in class. Research paper: The research paper will be worth 100 points and will involve either (a) replicating the results of an existing paper, and critically extending it further if possible, or (b) presenting original research. Typically the paper will be chosen by the student in consultation with the instructor and should have the following characteristics: (1) the paper must analyze a heterodox macro/pe question, and (2) the paper must use time series econometric analysis. (I have provided a small list of recent heterodox macro/pe papers that have used time series econometric analysis; students can choose a paper from this list or from any other appropriate source). Tentative schedule: The tentative schedule for the course is as follows: Week 1-2: Introduction to time series analysis and Difference Equations (Chapter 1 of the textbook): after revising basic concepts from probability and statistics (random variable, probability density/mass function, expectation, variance, covariance, etc.), the first two weeks will help familiarize us with two of the basic building blocks of time series econometrics, deterministic difference equations and lag operators. Week 3-5: Stationary Time Series Models (Chapter 2 of the textbook): moving from the analysis of deterministic to stochastic difference equations will equip us with the tools to understand the widely 2

used class of stationary time series models, the ARMA(p,q) model; here we will also go over basic notions of time series analysis and familiarize ourselves with the Box-Jenkins modeling strategy. Week 6-8: Models with Trends (Chapter 4 of the textbook): time series with trends, both deterministic (time trend) and stochastic (unit roots), are non-stationary random variables and require a whole new approach of analysis and statistical inference; this part of the course will introduce the basic issues involved in analyzing time series with trends (e.g., why do standard methods of inference, using t and F tests, completely break down when there is a unit root non-stationary regressor? how do we test for the presence of unit roots?) Week 9-11: Vector Time Series Models (Chapter 5 of the textbook): having studied univariate time series models in some detail, we will now move to the study of vector processes; in this part of the course we will study one of the widely used tools of dynamic macroeconomic analysis, vector autoregressions (VARs) and its three specific techniques - impulse response functions, variance decomposition and Granger causality. Week 12-14: Cointegration and Error Correction (Chapter 6 of the textbook): this part of the course will familiarize us with techniques used to study cointegrated random variables (i.e., unit root non-stationary random variables, a linear combinations which becomes stationary) and help answer questions like: How do we test for cointegration? what meaning can be attached to the notion of cointegrated variables? What is an error correction representation of a cointegrated system? How to carry out statistical inference on cointegrating vectors? References [1] Alexiou, C. 2010. A Keynesian-Kaleckian model of investment determination: a panel data investigation, Journal of Post Keynesian Economics, Vol. 32, No. 3, pp. 427-44. [2] Barbosa-Filho, N. H. and L. Taylor. 2006. Distributive And Demand Cycles In The US Economy-A Structuralist Goodwin Model, Metroeconomica, Vol. 57(3), pages 389-411, 07. (uses VAR methodology) 3

[3] Barbosa-Filho, N. H., Rada von Arnim, C., Taylor, L. and L. Zamparelli. 2008. Cycles and trends in U.S. net borrowing flows, Journal of Post Keynesian Economics, vol. 30(4), pages 623-648, July. [4] Bryant, W. D. and Joyeux, R. 2010. Interest linkages between the US, UK and German interest rates: should the UK join the European Monetary Union? International Review of Applied Economics, Vol. 24(6), pp. 633-647. [5] Fazzari, S., Hubbard, R. G., Petersen, B.C., Blinder, A.S., and J. M. Poterba. 1988. Financing Constraints and Corporate Investment, Brookings Papers on Economic Activity, Vol. 1988 (1), pp. 141-206. [6] Goldstein, J. P. 1999. Predator-Prey Model Estimates of the Cyclical Profit Squeeze, Metroeconomica, Vol. 50(2), pp. 139-173. (uses the structural VAR methodology) [7] Greiner, A., Rubart, J., and Semmler, W. 2004. Economic Growth, Skill-biased Technical Change and Wage Inequality: A Model and Estimations for the US and Europe, Journal of Macroeconomics, Vol. 26(4), pp. 597-621. [8] Hein, E. and C. Ochsen. 2003. Regimes of Interest Rate, Income Shares, Savings and Investment: A Kaleckian Model and Empirical Estimations for Some Advanced OECD Countries, Metroeconomica, Vol. 54(4), pp. 404-433. (uses time series regressions) [9] Hein, E. and A. Tarassow. 2010. Distribution, aggregate demand and productivity growth: theory and empirical results for six OECD countries based on a post-kaleckian model, Cambridge Journal of Economics, Vol. 34(4), pp. 727-754. [10] Heintz, J. 2010. The impact of public capital on the US private economy: new evidence and analysis, International Review of Applied Economics, Vol. 24(5), pp. 619-632. (uses cointegration analysis) [11] Hoffmann, A. 2010. An Overinvestment Cycle in Central and Eastern Europe Metroeconomica, Vol. 61(4), pp. 711-734. (uses the VAR methodology and Granger causality tests) 4

[12] Jayadev, A. 2007. Capital Account Openness and the Labour Share of Income, Cambridge Journal of Economics, Vol. 31, No. 3, pp. 423-443. [13] Leon-Ledesma, M. A., P. McAdam and A. Willman. 2010. Identifying the Elasticity of Substitution with Biased Technical Change, American Economic Review, Vol. 100(4), pages 1330-57, September. [14] Lopez, J., Sanchez, A., and A. Spanos. 2010. Macroeconomic Linkages in Mexico, Metroeconomica, forthcoming. (uses VAR, cointegration and ECM methodology) [15] Marquetti, A. 2004. Do Rising Real Wages Increase The Rate Of Labor- Saving Technical Change? Some Econometric Evidence, Metroeconomica, Vol. 55(4), pages 432-441, November. (uses cointegration and Granger causality tests) [16] Matthews, P. H. 2000. An Econometric Model of the Circuit of Capital, Metroeconomica, Vol 51(1), pp. 1-39. (unit root tests, GMM estimation) [17] McCloskey, D. N., and S. T. Ziliak. 1996. The Standard Error of Regressions, Journal of Economic Literature, Vol. XXXIV, pp. 97-114. [18] Pollin, R. 1991. Two Theories of Money Supply Endogeneity: Some Empirical Evidence, Journal of Post Keynesian Economics, Vol 13(3), pp. 366-396. (uses Granger causality tests) [19] Rafiq, S. 2010. Fiscal stance, the current account and the real exchange rate: Some empirical estimates from a time-varying framework, Structural Change and Economic Dynamics, Vol. 21, pp. 276290. (uses VAR with time-varying parameters) [20] Sarich, J., and J. Hecht. 2010. Competition and International Equity Returns: Some Empirical Tests of Turbulent Arbitrage, Review of Radical Political Economics, Vol 42., No. 1., pp. 5-31. (uses Johansen s cointegration methodology and an error correction framework) [21] Semmler, W. 2001. Statistical Estimation and Moment Evaluation of a Stochastic Growth Model with Asset Market Restrictions, Journal of Economic Behavior and Organization, Vol. 44(1), pp. 85-103. 5

[22] Semmler, Willi. 2004. Endogenous Growth: Estimating the Romer Model for the US and Germany, Oxford Bulletin of Economics and Statistics, Vol. 66, no. 2: 147-164. [23] Singh, T. 2009. Testing the neoclassical long-run and the Keynesian short-run effects of investment on output and growth in India, Journal of Post Keynesian Economics, Vol. 31, No. 2, pp. 271-298. [24] Stock, J. H., and M. W. Watson. 1988. Variable Trends in Economic Time Series, Journal of Economic Perspectives, Vol. 2(3), pp. 147-174. [25] Stock, J. H., and M. W. Watson. 2001. Vector Autoregressions, Journal of Economic Perspectives, Vol. 15(4), pp. 101-115. [26] Stockhammer, E., and O. Onaran. 2004. Accumulation, Distribution and employment: A Structural VAR approach to a Kaleckian macro model, Structural Change and Economic Dynamics, Vol. 15, pp. 421-447. (uses a structural VAR analysis) [27] Stockhammer, E., Onaran, O., and S. Ederer. 2009. Determinants of Functional Income Distribution in OECD Countries, Cambridge Journal of Economics, Vol. 33(1), pp. 139-59. [28] Stockhammer, E., Hein, E., and L. Grafl. 2011. Globalization and the effects of changes in functional income distribution on aggregate demand in Germany, International Review of Applied Economics, Vol. 25(1), pp. 1-23. [29] Tarassow, A. 2010. The Empirical Relevance of Goodwin s Business Cycle Model of the US Economy, MPRA Paper No. 22271, Munich. (Available at: http://mpra.ub.uni-muenchen.de/22271/) [30] Treeck, T. V. 2008. Reconsidering the Investment-Profit Nexus in Finance-led Economies: An ARDL-based Approach, Metroeconomica, Vol. 59(3), pp. 371-404. 6