January Examinations 2012

Similar documents
RELATIONSHIP BETWEEN VOLATILITY AND TRADING VOLUME: THE CASE OF HSI STOCK RETURNS DATA

Fall 2009 Social Sciences 7418 University of Wisconsin-Madison. Problem Set 2 Answers (4) (6) di = D (10)

F-Tests and Analysis of Variance (ANOVA) in the Simple Linear Regression Model. 1. Introduction

Data Collection Definitions of Variables - Conceptualize vs Operationalize Sample Selection Criteria Source of Data Consistency of Data

UNIVERSITAT AUTÒNOMA DE BARCELONA MARCH 2017 EXAMINATION

PhD/MA Econometrics Examination. January, 2019

( t) Outline of program: BGC1: Survival and event history analysis Oslo, March-May Recapitulation. The additive regression model

Modeling and Forecasting Volatility Autoregressive Conditional Heteroskedasticity Models. Economic Forecasting Anthony Tay Slide 1

THEORETICAL AUTOCORRELATIONS. ) if often denoted by γ. Note that

Advanced time-series analysis (University of Lund, Economic History Department)

a. (All your answers should be in the letter!

Economics 120C Final Examination Spring Quarter June 11 th, 2009 Version A

Professor Chris Murray. Midterm Exam

Econ107 Applied Econometrics Topic 5: Specification: Choosing Independent Variables (Studenmund, Chapter 6)

2. SPATIALLY LAGGED DEPENDENT VARIABLES

A First Guide to Hypothesis Testing in Linear Regression Models. A Generic Linear Regression Model: Scalar Formulation

Robustness Experiments with Two Variance Components

NPTEL Project. Econometric Modelling. Module23: Granger Causality Test. Lecture35: Granger Causality Test. Vinod Gupta School of Management

Evaluation of GARCH model Adequacy in forecasting Non-linear economic time series data

Lecture 6: Learning for Control (Generalised Linear Regression)

John Geweke a and Gianni Amisano b a Departments of Economics and Statistics, University of Iowa, USA b European Central Bank, Frankfurt, Germany

In the complete model, these slopes are ANALYSIS OF VARIANCE FOR THE COMPLETE TWO-WAY MODEL. (! i+1 -! i ) + [(!") i+1,q - [(!

Probabilistic Forecasting of Wind Power Ramps Using Autoregressive Logit Models

The Impact of SGX MSCI Taiwan Index Futures on the Volatility. of the Taiwan Stock Market: An EGARCH Approach

Bayesian Inference of the GARCH model with Rational Errors

Department of Economics University of Toronto

CHAPTER FOUR REPEATED MEASURES IN TOXICITY TESTING

Additive Outliers (AO) and Innovative Outliers (IO) in GARCH (1, 1) Processes

Lecture 15. Dummy variables, continued

Garched investment decision making with real risk

Lecture VI Regression

(10) (a) Derive and plot the spectrum of y. Discuss how the seasonality in the process is evident in spectrum.

On One Analytic Method of. Constructing Program Controls

5th International Conference on Advanced Design and Manufacturing Engineering (ICADME 2015)

Midterm Exam. Thursday, April hour, 15 minutes

Solution in semi infinite diffusion couples (error function analysis)

NATIONAL UNIVERSITY OF SINGAPORE PC5202 ADVANCED STATISTICAL MECHANICS. (Semester II: AY ) Time Allowed: 2 Hours

Analysis And Evaluation of Econometric Time Series Models: Dynamic Transfer Function Approach

DYNAMIC ECONOMETRIC MODELS Vol. 8 Nicolaus Copernicus University Toruń 2008

Final Exam Applied Econometrics

Volatility Interpolation

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 4

Time series Decomposition method

Economic Integration and Structure Change in Stock Market Dependence: Empirical Evidences of CEPA

Licenciatura de ADE y Licenciatura conjunta Derecho y ADE. Hoja de ejercicios 2 PARTE A

Stationary Time Series

Relative Efficiency and Productivity Dynamics of the Metalware Industry in Hanoi

PhD/MA Econometrics Examination. August PART A (Answer any TWO from Part A)

EFFICIENCY EVALUATION IN MODELLING STOCK DATA USING ARCH AND BILINEAR MODELS ADOLPHUS WAGALA

CHAPTER 5: MULTIVARIATE METHODS

Graduate Macroeconomics 2 Problem set 5. - Solutions

EDO UNIVERSITY, IYAMHO EDO STATE, NIGERIA DEPARTMENT OF ECONOMICS

New M-Estimator Objective Function. in Simultaneous Equations Model. (A Comparative Study)

The volatility modelling and bond fund price time series forecasting of VUB bank: Statistical approach

Appendix H: Rarefaction and extrapolation of Hill numbers for incidence data

Chapter 8 Dynamic Models

CHAPTER 10: LINEAR DISCRIMINATION

An introduction to Support Vector Machine

Introduction to Boosting

Kayode Ayinde Department of Pure and Applied Mathematics, Ladoke Akintola University of Technology P. M. B. 4000, Ogbomoso, Oyo State, Nigeria

Outline. 9. Heteroskedasticity Cross Sectional Analysis. Homoskedastic Case

ACEI working paper series RETRANSFORMATION BIAS IN THE ADJACENT ART PRICE INDEX

Outline. Probabilistic Model Learning. Probabilistic Model Learning. Probabilistic Model for Time-series Data: Hidden Markov Model

Normal Random Variable and its discriminant functions

National Exams December 2015 NOTES: 04-BS-13, Biology. 3 hours duration

Chapter 6: AC Circuits

Local Cost Estimation for Global Query Optimization in a Multidatabase System. Outline

Inverse Test Confidence Intervals for Turning points: A Demonstration with Higher Order Polynomials. J. N. Lye and J. G. Hirschberg.

( ) [ ] MAP Decision Rule

V.Abramov - FURTHER ANALYSIS OF CONFIDENCE INTERVALS FOR LARGE CLIENT/SERVER COMPUTER NETWORKS

Lecture 18: The Laplace Transform (See Sections and 14.7 in Boas)

Multivariate GARCH modeling analysis of unexpected U.S. D, Yen and Euro-dollar to Reminibi volatility spillover to stock markets.

Standard Error of Technical Cost Incorporating Parameter Uncertainty

The Use of ARCH and GARCH Models for Estimating and Forecasting Volatility

ECONOMETRICS - FINAL EXAM, 3rd YEAR (GECO & GADE)

Approximate Analytic Solution of (2+1) - Dimensional Zakharov-Kuznetsov(Zk) Equations Using Homotopy

Math 128b Project. Jude Yuen

Common persistence in conditional variance: A reconsideration. chang-shuai Li

Is it necessary to seasonally adjust business and consumer surveys. Emmanuelle Guidetti

US Monetary Policy and the G7 House Business Cycle: FIML Markov Switching Approach

Stochastic Programming handling CVAR in objective and constraint

Regression with Time Series Data

Childhood Cancer Survivor Study Analysis Concept Proposal

Panel Data Regression Models

Machine Learning Linear Regression

( ) () we define the interaction representation by the unitary transformation () = ()

Political Economy of Institutions and Development: Problem Set 2 Due Date: Thursday, March 15, 2019.

Volatility Modelling of the Nairobi Securities Exchange Weekly Returns Using the Arch-Type Models

Including the ordinary differential of distance with time as velocity makes a system of ordinary differential equations.

CS286.2 Lecture 14: Quantum de Finetti Theorems II

Lecture 11 SVM cont

GMM parameter estimation. Xiaoye Lu CMPS290c Final Project

Maximum Likelihood Estimation of Binary Dependent Variables Models: Probit and Logit. 1. General Formulation of Binary Dependent Variables Models

Advanced Macroeconomics II: Exchange economy

MODELING TIME-VARYING TRADING-DAY EFFECTS IN MONTHLY TIME SERIES

TSS = SST + SSE An orthogonal partition of the total SS

Endogeneity. Is the term given to the situation when one or more of the regressors in the model are correlated with the error term such that

Clustering with Gaussian Mixtures

Application of Vector Error Correction Model (VECM) and Impulse Response Function for Analysis Data Index of Farmers Terms of Trade

Empirical Tests of Asset Pricing Models with Individual Assets: Resolving the Errors-in-Variables Bias in Risk Premium Estimation

Transcription:

Page of 5 EC79 January Examnaons No. of Pages: 5 No. of Quesons: 8 Subjec ECONOMICS (POSTGRADUATE) Tle of Paper EC79 QUANTITATIVE METHODS FOR BUSINESS AND FINANCE Tme Allowed Two Hours ( hours) Insrucons o canddaes Answer FOUR quesons. Make sure ha you answer TWO quesons from Secon A and TWO quesons from Secon B. Equal marks are gven o each queson. SECTION A: MATHEMATICS (Answer TWO quesons). (a) Evaluae (calculae) he followng: () () () (v) (v) [%] Usng any mehod, fnd he nverse of he followng marx. A [%]

EC79 (c) Express he followng equaons n marx form and solve hem by marx nverson. Also solve hem by Cramer s rule or by he Gauss-Jordan elmnaon mehod. 6x ( x x x ) x x x x ( x x x x ) [%]. Fnd saonary values, f any, of he followng funcons, usng he second order condons o classfy hem: () () z w w x x y y [5%] z w w x x y y [5%] () z wx w 8w x [%] (v) [%] (v) z w 8w x x [%]. (a) Fnd saonary values for he followng funcon subjec o he consran ndcaed and ndcae wheher s a maxmum, mnmum or oherwse. Subjec o: [8%] If an addonal consran ha w + x = 6 s added o he problem n (a) wha effec does hs have? [%]. (a) A Bank makes hree sors of loans. The value of hgh rsk loans s H, of medum rsk loans s M and of low rsk loans s L. Toal profs from he nvesmens are log H log M log L. Reurns o each sor of loan are, β, γ. The Bank has I o nves n all loans. Wha s he value of each ype of loan f he Bank maxmses s profs? Check he second order condons. [75%] How do he proporons of he nvesmen n each ype of loan change as he reurns and he oal avalable for nvesmen change? [5%] Page of 5

EC79 SECTION B: ECONOMETRICS (Answer TWO quesons). (a) Explan he hree dfferen mehods of esmang parameers of a regressons funcon [5%] Wha s heeroscedascy? How can be addressed? Gve Example(s) [5%]. A researcher has esmaed he followng earnngs funcon on 5 ndvduals. The dependen varable s log of wages(lnwage) whch s regressed on a se of explanaory varables such as years (.e. years of schoolng compleed by he ndvdual), lnage (.e. log of age of he ndvdual) and male (.e. a bnary varable whch assumes a value of f he ndvdual s male and oherwse). Hence, he esmang equaon can be gven as: ln wage ( years ) (ln age ) ( male) The E-Vews oupu of he esmaon s gven below. Followng he resuls able here are quesons ha you are requred o answer. Dependen Varable: LNWAGE Mehod: Leas Squares Dae: //9 Tme: :6 Sample: 7 Included observaons: 5 Varable Coeffcen Sd. Error -Sasc Prob. C -.7885.999 -.7565.85 YEARS.97.8.56. LNAGE.688.7 5.959. MALE -.885.67 -.598.956 R-squared.5968 Mean dependen var 5.796 Adjused R-squared.5695 S.D. dependen var.97 S.E. of regresson.886 Akake nfo creron.5776 Sum squared resd 79.997 Schwarz creron.695 Log lkelhood -.67 Hannan-Qunn crer..5859 F-sasc.669 Durbn-Wason sa.985 Prob(F-sasc). a. Tes he hypohess a % level of sgnfcance. Inerpre he es resuls. [%] b. Inerpre each of he slope coeffcens. [%] Page of 5

EC79 c. Tes he hypohess ha all he coeffcens are equal o zero. Inerpre your resul. [%] d. Sugges how he specfcaon of he wage funcon can be mproved. [%]. Consder he process y.y.y. 5 where s a whe nose process. a. Show wheher y s a saonary or a non-saonary process. [%] b. Show ha y y y follows an ARMA process. [%] c. Show ha y follows an AR process of nfne order. [%] d. Show ha y follows an MA process of nfne order.[%]. () Wha s a saonary seres? Explan he dfferen mehods of esng for un roos. [5%] () An economercan has esmaed he followng model for he reurns for he FTSE ndex, r w var(,,...) where r s he reurn for FTSE ndex and esmaed oupu from Evews s as follows: s an unobserved whe nose process. The Dependen Varable: RET_FTSE Mehod: ML - ARCH (Marquard) - Normal dsrbuon Dae: //9 Tme: :5 Sample (adjused): 57 Included observaons: 57 afer adjusmens Convergence acheved afer eraons Bollerslev-Wooldrdge robus sandard errors & covarance Presample varance: backcas (parameer =.7) GARCH = C() + C()RESID(-)^ + C()GARCH(-) Varable Coeffcen Sd. Error z-sasc Prob. C.5..589. Varance Equaon C.86E-6.7E-7.98678. RESID(-)^.895.75 7.58875. GARCH(-).8995.8 79.98. R-squared -.57 Mean dependen var.9 Adjused R-squared -.57 S.D. dependen var.89 S.E. of regresson.9 Akake nfo creron -6.58675 Sum squared resd.665 Schwarz creron -6.579 Log lkelhood 877.77 Hannan-Qunn crer. -6.585 Durbn-Wason sa.958 Page of 5

EC79 (a) Inerpre he esmaed values for and. Is here here evdence of hgh perssence n volaly? [%] Show ha model above can be wren as an ARCH model of nfne order. [%] END OF PAPER Page 5 of 5