Carrying out an Empirical Project n A researcher conducting an empirical study follows these basic steps : –formulate a model –gather the data –estimate.

Slides:



Advertisements
Similar presentations
Econometric Modelling
Advertisements

F-tests continued.
Financial Analysis, Planning and Forecasting Theory and Application By Alice C. Lee San Francisco State University John C. Lee J.P. Morgan Chase Cheng.
LECTURE 9 : EMPRICIAL EVIDENCE : CAPM AND APT
Topic 2: Statistical Concepts and Market Returns
Portfolio Analysis and Theory
Return, Risk, and the Security Market Line
Empirical Evidence on Security Returns
Lecture 23 Multiple Regression (Sections )
1 4. Multiple Regression I ECON 251 Research Methods.
Economics 20 - Prof. Anderson1 Summary and Conclusions Carrying Out an Empirical Project.
Risk Premium Puzzle in Real Estate: Are real estate investors overly risk averse? James D. Shilling DePaul University Tien Foo Sing National University.
Week 14 Chapter 16 – Partial Correlation and Multiple Regression and Correlation.
Forecasting Revenue: An Example of Regression Model Building Setting: Possibly a large set of predictor variables used to predict future quarterly revenues.
Copyright © 2003 Pearson Education, Inc. Slide 5-1 Chapter 5 Risk and Return.
1 Chapter 2: Risk & Return Topics Basic risk & return concepts Stand-alone risk Portfolio (market) risk Relationship between risk and return.
Portfolio Management Lecture: 26 Course Code: MBF702.
Assessment of default probability in conditions of cyclicality Totmyanina Ksenia Moscow, 2014.
PowerPoint presentation to accompany Research Design Explained 6th edition ; ©2007 Mark Mitchell & Janina Jolley Chapter 7 Introduction to Descriptive.
Writing an Empirical Research Report, and Sources of Economic Data Prepared by Vera Tabakova, East Carolina University.
JDS Special program: Pre-training1 Carrying out an Empirical Project Empirical Analysis & Style Hint.
Forecasting Revenue: An Example of Regression Model Building Setting: Possibly a large set of predictor variables used to predict future quarterly revenues.
ERES2010 page. Chihiro SHIMIZU Estimation of Redevelopment Probability using Panel Data -Asset Bubble Burst and Office.
Risks and Rates of Return
Requests for permission to make copies of any part of the work should be mailed to: Thomson/South-Western 5191 Natorp Blvd. Mason, OH Chapter 11.
Lecture 10 The Capital Asset Pricing Model Expectation, variance, standard error (deviation), covariance, and correlation of returns may be based on.
● Final exam Wednesday, 6/10, 11:30-2:30. ● Bring your own blue books ● Closed book. Calculators and 2-page cheat sheet allowed. No cell phone/computer.
Copyright © 2009 Pearson Prentice Hall. All rights reserved. Chapter 5 Risk and Return.
Size Effect Matthew Boyce Huibin Hu Rajesh Raghunathan Lina Yang.
Comm W. Suo Slide 1. Comm W. Suo Slide 2 Diversification  Random selection  The effect of diversification  Markowitz diversification.
Copyright © 2015 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written consent of McGraw-Hill Education.
Determinants of Credit Default Swap Spread: Evidence from the Japanese Credit Derivative Market.
The Land Leverage Hypothesis Land leverage reflects the proportion of the total property value embodied in the value of the land (as distinct from improvements),
Chapter 10 Capital Markets and the Pricing of Risk.
Chapter 10 Capital Markets and the Pricing of Risk
Economics 173 Business Statistics Lecture 20 Fall, 2001© Professor J. Petry
Copyright © 2009 Pearson Prentice Hall. All rights reserved. Chapter 5 Risk and Return.
McGraw-Hill/Irwin Copyright © 2005 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 13 Empirical Evidence on Security Returns.
Chapter Return, Risk, and the Security Market Line McGraw-Hill/IrwinCopyright © 2012 by The McGraw-Hill Companies, Inc. All rights reserved. 12.
C M Clarke-Hill1 Analysing Quantitative Data Forming the Hypothesis Inferential Methods - an overview Research Methods.
Finance 300 Financial Markets Lecture 3 Fall, 2001© Professor J. Petry
Why Do Countries Use Capital Controls? Prepared by R. Barry Johnston and Natalia T. Tamirisa - December 1998 Presented by: Alyaa Ezzat.
LECTURE 10 : APPLICATION OF LINEAR FACTOR MODELS (Asset Pricing and Portfolio Theory)
Chapter 6 Market Equilibrium. McGraw-Hill/Irwin © 2004 The McGraw-Hill Companies, Inc., All Rights Reserved. The seminal work of Sharpe (1964) and Lintner.
INVESTMENTS | BODIE, KANE, MARCUS Copyright © 2014 McGraw-Hill Education. All rights reserved. No reproduction or distribution without the prior written.
Feasibility Study.
Sociological Research Methods. The Research Process Sociologists answer questions about society through empirical research (observation and experiments)
Chapter 9 CAPITAL ASSET PRICING AND ARBITRAGE PRICING THEORY The Risk Reward Relationship.
BUILDING THE REGRESSION MODEL Data preparation Variable reduction Model Selection Model validation Procedures for variable reduction 1 Building the Regression.
1 Prof. Dr. Rainer Stachuletz Summary and Conclusions Carrying Out an Empirical Project.
Chap 6 Further Inference in the Multiple Regression Model
1 CHAPTER 2 Risk and Return. 2 Topics in Chapter 2 Basic return measurement Types of Risk addressed in Ch 2: Stand-alone (total) risk Portfolio (market)
2 - 1 Copyright © 2002 by Harcourt College Publishers. All rights reserved. Chapter 2: Risk & Return Learning goals: 1. Meaning of risk 2. Why risk matters.
Copyright © 2003 South-Western/Thomson Learning. All rights reserved. The Capital Asset Pricing Model (CAPM) The CAPM has –A macro component explains risk.
1 CHAPTER 6 Risk, Return, and the Capital Asset Pricing Model (CAPM)
International portfolio diversification benefits: Cross-country evidence from a local perspective Authors of the Paper: Joost Driessen Luc Laeven Presented.
Sociology. Sociology is a science because it uses the same techniques as other sciences Explaining social phenomena is what sociological theory is all.
1 Assessment and Interpretation: MBA Program Admission Policy The dean of a large university wants to raise the admission standards to the popular MBA.
Predicting Energy Consumption in Buildings using Multiple Linear Regression Introduction Linear regression is used to model energy consumption in buildings.
Topic 3 (Ch. 8) Index Models A single-factor security market
F-tests continued.
FUNCTIONAL FORMS OF REGRESSION MODELS
Chow test.
Chapter 6: Autoregressive Integrated Moving Average (ARIMA) Models
AN INTRODUCTION TO EDUCATIONAL RESEARCH.
Competition, financial innovation and commercial
Week 14 Chapter 16 – Partial Correlation and Multiple Regression and Correlation.
Carrying out an Empirical Project
Chapter 9 Dummy Variables Undergraduated Econometrics Page 1
Presentation transcript:

Carrying out an Empirical Project n A researcher conducting an empirical study follows these basic steps : –formulate a model –gather the data –estimate the model –subject the model to hypothesis testing –interpret the results n Model formulation- –Single equation models –Simultaneous equation models –Examples-

n Hedonic price index model- –in this model the price of a commodity depends on its characteristics. For example, we have a real estate agent who wants to relate the sales price of a house to its characteristics: lot size, living area, number of bedrooms and bathrooms, types of built-in appliances, whether or not it has a swimming pool, whether it has a view, etc. In this model the marginal effect of a characteristic on the price is the “shadow value” of the characteristic. –Simple hedonic model Price= a + bSqft + cBaths + dBedrms n Capital Asset Pricing Model (CAPM) –this model provides a general framework for analyzing risk-return relationships for assets. Let r be the return on a particular security, rm be the return on the market portfolio, and rf be the return of a risk-free return. Let Y=r-rf be the excess returns of the market average portfolio. Then the following is the standard CAPM model: Y=bx+u –A security for which the beta is larger than one is more volatile than the market and one for which the beta is smaller than one is less.

n Data Gathering n Model estimation n Hypothesis Testing n Interpretation of the Results n Select a topic? –One systematic way to approach the problem of choosing a specific topic is to utilize the classification system of the Journal of Economic Literature. Scan in table 14.1 (p. 652) from R n Review the literature –again the JEL is a good place to start n Collection of the Data- –where do you go? For data at the international level one can go to the International Financial Statistics (IMF), World Development Report (World Bank), Penn World Tables For data at the national level-US data from the BLS, NBER, Federal Reserve Board

For data at the regional or state level there is state-by-state the Economic Report of the Governor which usually has statistical appendices. There is also the State and Metropolitan Data Book which is a supplement to the Statistical Abstract of the Unite States. Specialized data sources include the Survey of Current Business, often organized by SIC codes (standard industry classification). Federal Reserve Bulletin has detailed financial statistics. Standard and Poors and Moody’s have ratings of securities and other financial information. Journals such as the Journal of Applied Econometrics, Journal of Business and Economic Statistics, American Economic Review, Journal of Money, Credit and Banking, have online archives of data used in empirical studies. n Preliminary Empirical Analysis –Box plots, check for the presence of outliers, summary statistics such as mean, median, standard deviations, coefficient of variation (one rule of thumb is to rule out variables whose CV<.05), and well as the correlation matrix. –If the data is a time series plot the series against time to get an understanding of possible periodicities as well as trend and growth rate properties.

n Model Estimation and Hypothesis Testing –If you have enough data split the sample into two parts. The first will be used to analyze alternative specifications and examine significance of particular explanatory variables, functional form, etc. The second is to be used for your final estimations based on what you have learned from the first subsample. –Next estimate the general model that you have formulated. Examine the fit (adjusted and unadjusted R-squared), significance and reasonableness of coefficients. Often this part of the analysis is complicated by poor initial results and may require a good bit of judgment. Diagnostics and formal specification checks for serial correlation, heteroskedasticity, nonlinearities, interactions, ommitted variables, and possible simulatenous equations bias can be assessed using a battery of Wald and Lagrange multiplier tests discussed in the Ramanathan text. –Once you have a specification that has met with formal statistical criteria as well as with the “smell test” of reasonableness then reestimate using the second subsample n Writing Up Your Results

–A suggested outline for writing an empirical report is as follows: Statement of the problem review of the literature formulation of the general model data sources and descriptions model estimation and hypothesis testing interpretation of results and conclusions limitations of the study and possible extensions acknowledgements references and tables