Introductory Econometrics for Finance

Product Information

Alternatively, it is possible to adjust a stock price time series so that the dividends are added back to generate a total return index. If pt were a total return index, returns generated using either of the two formulae presented above thus provide a measure of the total return that would accrue to a holder of the asset during time t. The academic finance literature generally employs the log-return formulation (also known as log-price relatives since they are the log of the ratio of this period’s price to the previous period’s price). Box 1.3 shows two key reasons for this. There is, however, also a disadvantage of using the log-returns. The simple return on a portfolio of assets is a weighted average of the simple returns on the individual assets: R pt = Conducting empirical research or doing a project or dissertation in finance 13.1 What is an empirical research project and what is it for? 13.2 Selecting the topic 13.3 Sponsored or independent research? 13.4 The research proposal 13.5 Working papers and literature on the internet 13.6 Getting the data The data required may be available electronically through a financial information provider, such as Reuters or from published government figures. Alternatively, the required data may be available only via a survey after distributing a set of questionnaires i.e. primary data. Step 3: choice of estimation method relevant to the model proposed in step 1 For example, is a single equation or multiple equation technique to be used? Step 4: statistical evaluation of the model What assumptions were required to estimate the parameters of the model optimally? Were these assumptions satisfied by the data or the model? Also, does the model adequately describe the data? If the answer is ‘yes’, proceed to step 5; if not, go back to steps 1--3 and either reformulate the model, collect more data, or select a different estimation technique that has less stringent requirements. Step 5: evaluation of the model from a theoretical perspective Are the parameter estimates of the sizes and signs that the theory or intuition from step 1 suggested? If the answer is ‘yes’, proceed to step 6; if not, again return to stages 1--3. Step 6: use of model When a researcher is finally satisfied with the model, it can then be used for testing the theory specified in step 1, or for formulating forecasts or suggested courses of action. This suggested course of action might be for an individual (e.g. ‘if inflation and GDP rise, buy stocks in sector X’), or as an input to government policy (e.g. ‘when equity markets fall, program trading causes excessive volatility and so should be banned’). In all of the above cases, it is clearly the time dimension which is the most important, and the analysis will be conducted using the values of the variables over time. Introduction What is econometrics? Is financial econometrics different from ‘economic econometrics’? Types of data Returns in financial modelling Steps involved in formulating an econometric model Points to consider when reading articles in empirical finance Econometric packages for modelling financial data Outline of the remainder of this book Further reading Appendix: Econometric software package suppliers

Creating a workfile page 15 Importing Excel data into the workfile 16 The workfile containing loaded data 17 Summary statistics for a series 19 A line graph 20 Summary statistics for spot and futures 41 Equation estimation window 42 Estimation results 43 Plot of two series 79 Stepwise procedure equation estimation window 103 Conducting PCA in EViews 126 Regression options window 139 Non-normality test results 164 Regression residuals, actual values and fitted series 168 Chow test for parameter stability 188 Plotting recursive coefficient estimates 190 CUSUM test graph 191 Estimating the correlogram 235 Plot and summary statistics for the dynamic forecasts for the percentage changes in house prices using an AR(2) 257 Plot and summary statistics for the static forecasts for the percentage changes in house prices using an AR(2) 258 This will usually involve the formulation of a theoretical model, or intuition from financial theory that two or more variables should be related to one another in a certain way. The model is unlikely to be able to completely capture every relevant real-world phenomenon, but it should present a sufficiently good approximation that it is useful for the purpose at hand. ln ( p1 / p0 ) = ln p1 − ln p0 ln ( p2 / p1 ) = ln p2 − ln p1 ln ( p3 / p2 ) = ln p3 − ln p2 ln ( p4 / p3 ) = ln p4 − ln p3 ln ( p5 / p4 ) = ln p5 − ln p4 ——————————– ln p5 − ln p0 = ln ( p5 / p0 ) Problems that could be tackled using time series data: ● How the value of a country’s stock index has varied with that country’s macroeconomic fundamentals ● How the value of a company’s stock price has varied when it announced the value of its dividend payment ● The effect on a country’s exchange rate of an increase in its trade deficit.The list in box 1.1 is of course by no means exhaustive, but it hopefully gives some flavour of the usefulness of econometric tools in terms of their financial applicability. Uncovered interest parity test results Forecast error aggregation Call bid--ask spread and trading volume regression 6.2 Put bid--ask spread and trading volume regression 6.3 Granger causality tests and implied restrictions on VAR models 6.4 Marginal significance levels associated with joint F-tests 6.5 Variance decompositions for the property sector index residuals 7.1 Critical values for DF tests (Fuller, 1976, p. 373) 7.2 DF tests on log-prices and returns for high frequency FTSE data 7.3 Estimated potentially cointegrating equation and test for cointegration for high frequency FTSE data 7.4 Estimated error correction model for high frequency FTSE data 7.5 Comparison of out-of-sample forecasting accuracy 7.6 Trading profitability of the error correction model with cost of carry 7.7 Cointegration tests of PPP with European data 7.8 DF tests for international bond indices 7.9 Cointegration tests for pairs of international bond indices 7.10 Johansen tests for cointegration between international bond yields 7.11 Variance decompositions for VAR of international bond yields In the limit, as the frequency of the sampling of the data is increased so that they are measured over a smaller and smaller time interval, the simple and continuously compounded returns will be identical. Forecasting covariances and correlations Covariance modelling and forecasting in finance: some examples Historical covariance and correlation Implied covariance models Exponentially weighted moving average model for covariances Multivariate GARCH models A multivariate GARCH model for the CAPM with time-varying covariances 8.28 Estimating a time-varying hedge ratio for FTSE stock index returns 8.29 Estimating multivariate GARCH models using EViews Appendix: Parameter estimation using maximum likelihood This is a good book introducing the general field of financial econometrics to students, assuming they have no prior knowledge of econometrics. Undergraduate, as well as beginning graduate, students should find the wide range of topics covered useful for not only getting a good toehold into the literature, but also to be able to apply the methods to data right away.' Prasad V. Bidarkota, Florida International University

Continuous and discrete data As well as classifying data as being of the time series or cross-sectional type, we could also distinguish it as being either continuous or discrete, exactly as their labels would suggest. Continuous data can take on any value and are not confined to take specific numbers; their values are limited only by precision. For example, the rental yield on a property could be 6.2%, 6.24% or 6.238%, and so on. On the other hand, discrete data can only take on certain values, which are usually integers1 (whole numbers), and are often defined to be count numbers. For instance, the number of people in a particular underground carriage or the number of shares traded during a day. In these cases, having 86.3 passengers in the carriage or 58571/2 shares traded would not make sense. Discretely measured data do not necessarily have to be integers. For example, until recently when they became ‘decimalised’, many financial asset prices were quoted to the nearest 1/16 or 1/32 of a dollar. A brief overview of the classical linear regression model What is a regression model? Regression versus correlation Simple regression Some further terminology Simple linear regression in EViews -- estimation of an optimal hedge ratio The assumptions underlying the classical linear regression model Properties of the OLS estimator Precision and standard errors An introduction to statistical inference This excellent book provides practical econometric solutions for empirical finance. It is an ideal textbook for introductory courses on financial econometrics …'

Author

Who should read this book? The intended audience is undergraduates or Masters/MBA students who require a broad knowledge of modern econometric techniques commonly employed in the finance literature. It is hoped that the book will also be useful for researchers (both academics and practitioners), who require an introduction to the statistical tools commonly employed in the area of finance. The book can be used for courses covering financial time-series analysis or financial econometrics in undergraduate or postgraduate programmes in finance, financial economics, securities and investments. Although the applications and motivations for model-building given in the book are drawn from finance, the empirical testing of theories in many other disciplines, such as management studies, business studies, real estate, economics and so on, may usefully employ econometric analysis. For this group, the book may also prove useful. Finally, while the present text is designed mainly for students at the undergraduate or Masters level, it could also provide introductory reading in financial time-series modelling for finance doctoral programmes where students have backgrounds which do not include courses in modern econometric techniques. Returns in financial modelling In many of the problems of interest in finance, the starting point is a time series of prices -- for example, the prices of shares in Ford, taken at 4p.m. each day for 200 days. For a number of statistical reasons, it is preferable not to work directly with the price series, so that raw price series are usually converted into series of returns. Additionally, returns have the added benefit that they are unit-free. So, for example, if an annualised return were 10%, then investors know that they would have got back £110 for a £100 investment, or £1,100 for a £1,000 investment, and so on. There are two methods used to calculate returns from a series of prices, and these involve the formation of simple returns, and continuously compounded returns, which are achieved as follows: Simple returns Rt = Parameter stability tests 4.13 A strategy for constructing econometric models and a discussion of model-building philosophies 4.14 Determinants of sovereign credit ratings Steps involved in forming an econometric model page 9 Scatter plot of two variables, y and x 29 Scatter plot of two variables with a line of best fit chosen by eye 31 Method of OLS fitting a line to the data by minimising the sum of squared residuals 32 Plot of a single observation, together with the line of best fit, the residual and the fitted value 32 Scatter plot of excess returns on fund XXX versus excess returns on the market portfolio 35 No observations close to the y-axis 36 Effect on the standard errors of the coefficient estimates when (xt − x¯ ) are narrowly dispersed 48 Effect on the standard errors of the coefficient estimates when (xt − x¯ ) are widely dispersed 49 Effect on the standard errors of xt2 large 49 Effect on the standard errors of xt2 small 50 The normal distribution 54 The t-distribution versus the normal 55 Rejection regions for a two-sided 5% hypothesis test 57 Rejection regions for a one-sided hypothesis test of the form H0 : β = β ∗ , H1 : β < β ∗ 57 Rejection regions for a one-sided hypothesis test of the form H0 : β = β ∗ , H1 : β > β ∗ 57 Critical values and rejection regions for a t20;5% 61

than deriving proofs and learning formulae ● To write an accessible textbook that required no prior knowledge of associated with them a particular frequency of observation or collection of data points. The frequency is simply a measure of the interval over, or the regularity with which, the data are collected or recorded. Box 1.2 shows some examples of time series data. A word on ‘As transactions occur’ is necessary. Much financial data does not start its life as being regularly spaced. For example, the price of common stock for a given company might be recorded to have changed whenever there is a new trade or quotation placed by the financial information recorder. Such recordings are very unlikely to be evenly distributed over time -- for example, there may be no activity between, say, 5p.m. when the market closes and 8.30a.m. the next day when it reopens; there is also typically less activity around the opening and closing of the market, and around lunch time. Although there are a number of ways to deal with this issue, a common and simple approach is simply to select an appropriate frequency, and use as the observation for that time period the last prevailing price during the interval. It is also generally a requirement that all data used in a model be of the same frequency of observation. So, for example, regressions that seek to estimate an arbitrage pricing model using monthly observations on macroeconomic factors must also use monthly observations on stock returns, even if daily or weekly observations on the latter are available. The data may be quantitative (e.g. exchange rates, prices, number of shares outstanding), or qualitative (e.g. the day of the week, a survey of the financial products purchased by private individuals over a period of time, a credit rating, etc.). Pt Pt − Pt−K Pt Pt−1 Pt−K +1 = = −1= × × ... × −1 Pt−K Pt−K Pt−1 Pt−2 Pt−K = [(1 + Rt )(1 + Rt−1 ) . . . (1 + Rt−K +1 )] − 1 (1.4) Modelling long-run relationships in finance Stationarity and unit root testing Testing for unit roots in EViews Cointegration Equilibrium correction or error correction models Testing for cointegration in regression: a residuals-based approach Methods of parameter estimation in cointegrated systems Lead--lag and long-term relationships between spot and futures markets Testing for and estimating cointegrating systems using the Johansen technique based on VARs Purchasing power parity Cointegration between international bond markets Testing the expectations hypothesis of the term structure of interest rates Testing for cointegration and modelling cointegrated systems using EViews there is an ever greater need for a textbook like this that applies relevant econometric topics to the field of finance. The book explains difficult concepts in a clear and easily understandable way, with plenty of real-world practical illustrations. A particularly welcome feature, and extremely helpful to students, is the use of examples with computer printouts on how to estimate models using the Eviews software. I highly recommend it.'Multivariate models Motivations Simultaneous equations bias So how can simultaneous equations models be validly estimated? Can the original coefficients be retrieved from the π s? Simultaneous equations in finance A definition of exogeneity Triangular systems Estimation procedures for simultaneous equations systems An application of a simultaneous equations approach to modelling bid--ask spreads and trading activity Simultaneous equations modelling using EViews Vector autoregressive models Does the VAR include contemporaneous terms? Block significance and causality tests VARs with exogenous variables Impulse responses and variance decompositions VAR model example: the interaction between property returns and the macroeconomy VAR estimation in EViews Box 1.1 The value of econometrics (1) Testing whether financial markets are weak-form informationally efficient (2) Testing whether the Capital Asset Pricing Model (CAPM) or Arbitrage Pricing Theory (APT) represent superior models for the determination of returns on risky assets (3) Measuring and forecasting the volatility of bond returns (4) Explaining the determinants of bond credit ratings used by the ratings agencies (5) Modelling long-term relationships between prices and exchange rates (6) Determining the optimal hedge ratio for a spot position in oil (7) Testing technical trading rules to determine which makes the most money (8) Testing the hypothesis that earnings or dividend announcements have no effect on stock prices (9) Testing whether spot or futures markets react more rapidly to news (10) Forecasting the correlation between the stock indices of two countries. What is econometrics? The literal meaning of the word econometrics is ‘measurement in economics’. The first four letters of the word suggest correctly that the origins of econometrics are rooted in economics. However, the main techniques employed for studying economic problems are of equal importance in financial applications. As the term is used in this book, financial econometrics will be defined as the application of statistical techniques to problems in finance. Financial econometrics can be useful for testing theories in finance, determining asset prices or returns, testing hypotheses concerning the relationships between variables, examining the effect on financial markets of changes in economic conditions, forecasting future values of financial variables and for financial decision-making. A list of possible examples of where econometrics may be useful is given in box 1.1. 1 Economic or financial theory (previous studies) 1b. Formulation of an estimable theoretical model 2. Collection of data 3. Model estimation 4. Is the model statistically adequate? No Reformulate model

assume that students of finance were well grounded in economic principles; econometrics would be taught using economic motivations and examples. However, finance as a subject has taken on a life of its own in recent years. Drawn in by perceptions of exciting careers and telephone-number salaries in the financial markets, the number of students of finance has grown phenomenally, all around the world. At the same time, the diversity of educational backgrounds of students taking finance courses has also expanded. It is not uncommon to find undergraduate students of finance even without advanced high-school qualifications in mathematics or economics. Conversely, many with PhDs in physics or engineering are also attracted to study finance at the Masters level. Unfortunately, authors of textbooks have failed to keep pace, thus far, with the change in the nature of students. In my opinion, the currently available textbooks fall short of the requirements of this market in three main regards, which this book seeks to address: (1) Books fall into two distinct and non-overlapping categories: the introductory and the advanced. Introductory textbooks are at the appropriate level for students with limited backgrounds in mathematics or statistics, but their focus is too narrow. They often spend too long deriving the most basic results, and treatment of important, interesting and relevant topics (such as simulations methods, VAR modelling, etc.) is covered in only the last few pages, if at all. The more advanced textbooks, meanwhile, usually require a quantum leap in the level of mathematical ability assumed of readers, so that such books cannot be used on courses lasting only one or two semesters, or where students have differing backgrounds. In this book, I have tried to sweep a broad brush over a large number of different econometric techniques that are relevant to the analysis of financial and other data. (2) Many of the currently available textbooks with broad coverage are too theoretical in nature and students can often, after reading such a book, still have no idea of how to tackle real-world problems themselves, even if they have mastered the techniques in theory. To this end, in this book, I have tried to present examples of the use of the techniques in finance, together with annotated computer instructions and sample outputs for an econometrics package (EViews). This should assist students who wish to learn how to estimate models for themselves -- for example, if they are required to complete a project or dissertation. Some examples have been developed especially for this book, while many others are drawn from the academic finance literature. In my opinion, this is an essential but rare feature of a textbook that should help to show students how econometrics is really applied. It is also hoped that this approach will encourage some students to delve deeper into the literature, and will give useful pointers and stimulate ideas for research projects. It should, however, be stated at the outset that the purpose of including examples from the academic finance print is not to provide a comprehensive overview of the literature or to discuss all of the relevant work in those areas, but rather to illustrate the techniques. Therefore, the literature reviews may be considered deliberately deficient, with interested readers directed to the suggested readings and the references therein. (3) With few exceptions, almost all textbooks that are aimed at the introductory level draw their motivations and examples from economics, which may be of limited interest to students of finance or business. To see this, try motivating regression relationships using an example such as the effect of changes in income on consumption and watch your audience, who are primarily interested in business and finance applications, slip away and lose interest in the first ten minutes of your course. Box 1.2 Time series data Series Industrial production Government budget deficit Money supply The value of a stock The fundamentals have been broadened into two introductory chapters (one covering mathematics and the other basic statistics) to provide a strong foundation for those new to the subject Motivations for the first edition This book had its genesis in two sets of lectures given annually by the author at the ICMA Centre (formerly ISMA Centre), University of Reading and arose partly from several years of frustration at the lack of an appropriate textbook. In the past, finance was but a small sub-discipline drawn from economics and accounting, and therefore it was generally safe toThis is a good book introducing the general field of financial econometrics to students, assuming they have no prior knowledge of econometrics. Undergraduate, as well as beginning graduate, students should find the wide range of topics covered useful for not only getting a good toehold into the literature, but also to be able to apply the methods to data right away.' Appendix 1 A review of some fundamental mathematical and statistical concepts A1 Introduction A2 Characteristics of probability distributions A3 Properties of logarithms A4 Differential calculus A5 Matrices A6 The eigenvalues of a matrix Is financial econometrics different from ‘economic econometrics’? As previously stated, the tools commonly used in financial applications are fundamentally the same as those used in economic applications, although the emphasis and the sets of problems that are likely to be encountered when analysing the two sets of data are somewhat different. Financial data often differ from macroeconomic data in terms of their frequency, accuracy, seasonality and other properties. In economics, a serious problem is often a lack of data at hand for testing the theory or hypothesis of interest -- this is often called a ‘small samples problem’. It might be, for example, that data are required on government budget deficits, or population figures, which are measured only on an annual basis. If the methods used to measure these quantities changed a quarter of a century ago, then only at most twenty-five of these annual observations are usefully available. Two other problems that are often encountered in conducting applied econometric work in the arena of economics are those of measurement error and data revisions. These difficulties are simply that the data may be estimated, or measured with error, and will often be subject to several vintages of subsequent revisions. For example, a researcher may estimate an economic model of the effect on national output of investment in computer technology using a set of published data, only to find that the Cross-sectional data Cross-sectional data are data on one or more variables collected at a single point in time. For example, the data might be on: ● A poll of usage of Internet stockbroking services ● A cross-section of stock returns on the New York Stock Exchange