Stat 434 upenn. Code Box Index (Stat 434 Wharton) Some Guides to S-Plus .

Stat 434 upenn forecast † Also review the information on these functions using the S-Plus help(). Stationarity: Logically the “whole banana” yet logically untestable (per the cycle construction) Statistics 434: Final Projects Project Overview The nominal task is either to design and test a “trading system,” or to develop and test a empirical thesis about return processes. Statistics 434 is NOT a course for everyone. These are test for stationarity of a time series, but, as will be stressed in class, these tests only detect speciflc kinds of non-stationarity. Statistics 434: Bullet Points for Day 18 Introduction to the post-GARCH ZOO We begin with a celebration of the model with that is AR(1) in \mean" Statistics 434: Homework No. Except Statistics 434: Bullet Points for Day 3 AR(1) Estimation | Point Estimates and Their Distributions The AR(1) model will serve as our \model for a model. This works forms the basis for Homework 5, which offers a bump-up in challenge. ’’ In other words, two securities with the same prices in all states of the world should sell for the same amount. edu/stat/ Instructors: Office: Office Hours: Lawrence Brown JMHH 445 Tue & Thurs 10 – 11 Statistics 434: Financial Time Series First Day Questionnaire Your Name and your E-Mail Address: Your School, Major, and Year of Study: How did you hear about this course? Friend? Advisor? Other? Something about yourself, such as where you grew up, or anything else that you would like me to know: Statistics 434: Bullet Points for Day 12 Fractional Kelly and the AR(p) Model Martingales, EMH, and Ruin We brie°y discuss fractional Kelly bet sizing and develop the wealth formula under the AR(p) model. Data Get four year’s (or a little less) of daily returns from CRSP for some firm, Statistics 434: Bullet Points for Day 19 More on Using GARCH and its Family Members The large number of models in the GARCH family tend to give one the feeling of wading in to a swamp. 2: An Experiment with Ljung-Box First recall the Ljung-Box Statistic on k lags: LB = T(T +2) Xk j=1 ρˆ j 2 T −j • Write an S-Plus function that computes a vector that holds the first 25 sample autocorrelations of a time series. forecast. e. Impact Multipliers (a) First Lag (b) K’th Lag (c) Long Run Efiect 3. Un-fortunately, both in academia and in industry, these topics are often oversold. In 2003 we were reminded that much of the mutual fund industry has suffered the taint of unethical practices which put the interests of one class of client above the interest of another class of client. Statistics 434: Final Projects Project Overview The nominal task is either to design and test a “trading system,” or to develop and test a empirical thesis about return processes. We will cover what we need to know about S-Plus in class, but if you want a further resource, you might take at look at Patrick Burn's A Guide for the Unwilling S User. You should check out his website if you think you have a question for which he has posted an answer that came up in office hours, etc. Statistics 434: Bullet Points for Day 6 WRDS, CRSP, Real Asset Returns, and Normality Assumptions The main task today is rock-bottom practical: How does one access the CRSP data via WRDS? We also ask “When is it feasible to treat a series of returns as if they are normally distributed?” This question has both “straightforward” and Statistics 434: Bullet Points for Day 11 Kelly Principle for the AR(1) Model; Introduction to EMH After a brief review of the Kelly principle for independent and identically distributed returns, we consider a return process given by an AR(1) model and we flnd explicit formulas for the bet size and for the wealth process. seed() and arima. Still, there are instances of forecastability. Incidentally, the Federal Reserve has extensive time series of interest rates. It is offered in the fall and does have the Statistics 434: Financial and Economic Time Series. 36, amending joint resolution of February 14, 1920 (41 stat. GARCH Basics 1. " That is, what we can see and say about AR(1) provides an outline of what we would hope to see or say about any of the other models that we will consider. Statistics 434 : Bullet Points for Day 11 Betting on AR(1) and an Introduction to EMHs After a brief review, we see what the Kelly criterion suggests when we con-sider a return process given by an AR(1) model. https://webcafe. Review the help flles on the functions set. Statistics 434: Bullet Points A Pre-Thanksgiving Interlude In the Wednesday afternoon before Thanksgiving, attendance typically runs under 60%, so the most practical to use of this time is to cover some special topics that one can miss without creating a gap in the core material everyone must know. Hint: The lion’s share of the Statistics 434 Homework No. non-significant Ljung-Box statistics for returns (under conven-tional model). ” Statistics 434: Bullet Points for Day 13 Stationarity and Unit Root Tests If a time series is not stationary, or cannot be transformed to be stationary — say by taking differences, then we are pretty close to stuck. wharton. Returns are not independent. 6 Stationarity, Extremes, and Opportunities Part 1: Checking Out the Unit Root Tests • Obtain 500 days of price and return data for a stock of your choosing. edu/stat/ Instructors: Office: Office Hours: Lawrence Brown JMHH 445 Tue & Thurs 10 – 11 e. You Statistics 434: Bullet Points for Day 1 Getting Started — Big Picture, S-Plus, Look at a Model The Bullet Point Day Plans serve to organize the class time and to provide you with quick reviews of what topics were covered. The ARCH models address this in the most straightforward way imaginable. If students and friends find it useful to link to the course page, then over time the Stat 434 Home Pages will get a decent page rank. equity bear markets (123 observations) U. sim, arima. In the not-to %PDF-1. Moreover, everyone knows that the riskiness of the investment should somehow Statistics 434: Bullet Points for Day 1 Getting Started — Big Picture, S-Plus, Look at a Model The Bullet Point Day Plans serve to organize the class time and to provide you with quick reviews of what topics were covered. With the notion of cointegration (with or without a hyphen) we enter new territory. Also review the information on these functions using the S-Plus help(). 7 Exploration of Style Momentum In the language of mutual funds, \style" has come to refer to the nine boxes into which Morningstar jams all funds. Dan will have office hours . Chen and Knez (1995) extend this to argue that ‘‘closely integrated markets should assign What you find here is the Course blog for the Fall 2009 Course "Stat 434". In this course, we will learn introductory statistics using R with a focus on the application of statistical thinking to business problems. In a way the stream is now a bit polluted. edu/stat/ Instructors: Office: Office Hours: Lawrence Brown JMHH 445 Tue & Thurs 10 – 11 Statistics 434: Bullet Points for Day 22 A Pre-Thanksgiving Interlude In the Wednesday afternoon before Thanksgiving, attendance typically runs under 60%, so the most practical to use of this time to cover some special topics that one can miss without creating a gap in the core material everyone must know. 3: WRDS and Testing for Normality As preparation, you should skim the material in Zivot and Wang on the creation of time series objects and the use of the timeDate() function, but the e-Handout WRDStoFinMet. Statistics 434: Bullet Points for Day 16 Switching Regressions and Other Non-Linear Ideas for Forecasting Returns We’ll go over the Clive Grainger’s article “Forecasting stock market prices: Lessons for forecasters. 5 Due Monday October 31. The moving average representation 2. You Statistics 434: Homework No. Code Box Index (Fall 2005) Richer Contexts . Moreover, everyone knows that the riskiness of the investment should somehow Statistics 434 Homework No. economic recessions (65 observations) 3-year beta Percentage Percentage to total Median Mean of months Median Mean of months Journal of Econometrics 31 (1986) 307-327. 3 %âãÏÓ 185 0 obj > endobj xref 185 19 0000000016 00000 n 0000001389 00000 n 0000001490 00000 n 0000001552 00000 n 0000001680 00000 n 0000001827 00000 n 0000001935 00000 n 0000002434 00000 n 0000003066 00000 n 0000003638 00000 n 0000003740 00000 n 0000004145 00000 n 0000007960 00000 n 0000008104 00000 n 0000014285 00000 n 0000018869 00000 n 0000019177 00000 n 0000019391 00000 n Statistics 434: Bullet Points for Day 8 ARIMA(p,d,q) In Full After considering the \stylized facts" suggested by HW3, we complete our description of the most widely used class of univariate time series models, the ARIMA(p,d,q) models. It is offered in the fall and does have the For this reason, and for the reason of coherence, it is no longer possible to audit Statistics 434. If you are shopping please do read the little piece I have written about expected changes and course expectations. Syllabus for Financial Time Series (Wharton Statistics 434) Course Description. For this assignment you’ll need a time series of length 1000 or so. In e. non-signi cant Ljung-Box statistics for returns (under conven-tional model). Statistics 434 Homework No. Confronted with so many alternatives, the modeler cannot help but wonder how to make a reasonable choice. 5. For this reason, and for the reason of coherence, it is no longer possible to audit Statistics 434. Our main task is to understand how the models re-ect structural properties of time series. Simulate a series Statistics 434: Bullet Points for Day 16 Dynamic Time Series Regression | Lag Models of Several Flavors † Autoregressive Distributed Lag Model (ADL Model) 1. The assumption of independence of returns is widely used in flnancial theory https://webcafe. What you find below is the blog for Stat 434 Financial Time Series Fall 2007. Moreover, everyone knows that the riskiness of the investment should somehow Statistics 434: Bullet Points for Day 22 Comparing Asset Returns in the Context of Risks Any asset manger, asset class, or investment strategy will be judged on the basis of the historical returns viewed in the context of the risks that were taken | but how? There are oodles of suggestions, yet if we are honest, none of these Statistics 434: Bullet Points for Day 6 WRDS, CRSP, Real Asset Returns, and Normality Assumptions The main task today is rock-bottom practical: How does one access the CRSP data via WRDS? We also ask \When is it feasible to treat a series of returns as if they are normally distributed?" This question has both \straightforward" and \tricky" aspects. This gives us our flrst encounter with the notion of stationarity and \long run distribution" | which is a trickier concept than you might guess. txt will have most of the news you can use. † Your real goal is to show that you have achieved a high level of skill Vile Practice: From the Shady to the Criminally Fraudulent . Almost any short term rate on the list would be appropriate and would not change the analysis. Statistics 434: Bullet Points for Day 2 Noise, AR(1), S-Plus, Estimation, and Simulation We begin with an exploration of the normal noise model, then we look at its simplest alternative, the AR(1) model. In particular, we consider the tools for simulation and for fltting. It’s not traditional to discuss martingales in the context of time series, but it is Statistics 434: Bullet Points for Day 3 AR(1) Estimation | Point Estimates and Their Distributions The AR(1) model will serve as our \model for a model. S. With the notion of cointegration (with or without Statistics 434: Final Projects Project Overview The nominal task is either to design and test a “trading system,” or to develop and test a empirical thesis about return processes. Statistics 434 : Bullet Points for Day 9 Simulating and Fitting ARIMA(p,d,q) Models The main formal task is to pick up the computation tools for studying the ARIMA(p,d,q) models. 4 ARMA, ACF, PACF, and a Betting Simulation Reading † Review the material in Zivot and Wang on arima. , 434), giving to discharged soldiers, sailors, and marines a preferred right of homestead or desert land entry. Hint: The lion’s share of the Statistics 434: Bullet Points for Day 15 Time Series Regression, CAPM, and the Three Factor Model For us, time series regressions are typified by the Capital Asset Pricing Model (CAPM) and the Fama French Three Factor Model (FF3FM). Shortages of natural gas lead the US Government to pass the 1978 Natu ral Gas Policy Act (NGPA). 1. You should look on them as being more like Statistics 434: Bullet Points for Day 10 Bet Sizing and Long-term Wealth Growth Rates Today we take a little side tour from our investigation of the ARIMA(p,d,q) model to look at what the general question “Facing the possibility of a favorable bet, what fraction of one’s wealth should one bet?” This question leads us to Engle's GARCH 101 is closely related to his Noble Lecture though the Nobel Lecture has a few parts that will not be transparent to 434 students. To still the animal spirits, we take up the contro- Statistics 434: Bullet Points for Day 24 Risk Adjusted Returns It is a simple fact that any mutual fund, investment manger, asset class, or investment strategy will be judged on the basis of its historical returns. Do take Considering 434 for Fall 2009? What you find below is the course blog for Fall 2008. Reading Review your class notes on the Kelly Principle for AR(1). Statistics 434: Bullet Points for Day 13 Stationarity and Unit Root Tests Chapter 4 of Zivot and Wang discusses what are known as Unit Root Tests. Data Get four year’s (or a little less) of daily returns from CRSP for some firm, Code Box Index (Stat 434 Wharton) Some Guides to S-Plus . If you are a graduate student, or a very well-prepared well-focused undergraduate you are encouraged to take a look at the closely related Statistics 956: Computational and Financial Statistics . We need to understand the conditions for stationarity of the AR(p) models, Statistics 434: Bullet Points for Day 5 Autocorrelation Tests | Especially the Ljung-Box Test When is it feasible to treat a series of returns as if they were independent? This is possibly the most basic question that one can ask about a series of flnancial returns. Moreover, they only Statistics 434: Homework No. † Simulation Using Statistics 434 Final Project Due Friday December 16 (12:00 Noon) Suite 400 JMHH Project Overview † The nominal task is either to design and test a \trading system," or to develop and test a empirical thesis about price processes. 1 Experience with S functions and Simulation • Write a function getrhohat() which creates a realization of ˆρ, the sample autocorrelation for the series {y t} which is a simulated realization of length T = 100 from a stationary AR model with ρ = 0. North-Holland GENERALIZED AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTICITY Tim BOLLERSLEV* University of California at San Diego, La Jolla, CA 92093, USA. The flrst part of this material mainly serves to reinforce what you have read in Kraus and Olson; the new material deals with Finmetrics. Reading † Review the material in Zivot and Whang on arima. ” This being so, we would surely like to The Online Books Page Instructions under house joint resolution 30, approved January 21, 1922, public resolution no. Explore the effect (if Statistics 434 Homework No. A further bene t of Statistics 434: Bullet Points for Day 7 AR(p) with p ≥ 2 We now consider the autoregressive models with p ≥ 2, beginning with a look at the most useful of these — the modest AR(2) model that was made famous by Yule’s study of sun spot data. We’ll also add to your tool kit by discussing the likelihood function and its major applications: Statistics 434: Bullet Points for Day 12 Martingales: The Most Important Stochastic Processes At the first level, martingales are simple mathematical objects that help us understand fair games, including the impossibility of effective gambling systems. We also start to consider Jul 25, 2002 · state pricing of OPEC. These are natural and important topics. ” This being so, we would surely like to Statistics 434 : Bullet Points for Day 11 Betting on AR(1) and an Introduction to EMHs After a brief review, we see what the Kelly criterion suggests when we con-sider a return process given by an AR(1) model. Simulation and Estimation of an AR(2) or ARIMA(2,0,0) process † Let `1 = 0:2, `2 = 0:15, and ¾ =:25 Statistics 434 Homework No. Aug 20, 2006 · Still, I won't erase things either, so if you are thinking about taking Stat 434 in the Fall of 2007, what you find here should give you an honest impression of what the course is all about. 3 Due Monday October 4. These styles are given by the cross table of (small, medium, large) capitalizations and (value, blend, growth) investment temperaments. 6 Farshid Magami Asl G63. I'll leave this bog up for a while so former students can have access to the resources and prospective students can have a idea of what our class is like. The blog structure also facilitates SEO. Statistics 434: Bullet Points for Day 24 Risk Adjusted Returns It is a simple fact that any mutual fund, investment manger, asset class, or investment strategy will be judged on the basis of its historical returns. 4 Due Monday October 10. First and Foremost . Time:Friday from 3 to 5pm ; Location: 427 Huntsman Hall ments with the same payoff in every state of nature must have the same current value. Statistics 434: Homework No. 8 Due Monday November 21. We need to understand the conditions for stationarity of the AR(p) models, Statistics 434: Bullet Points for Day 2 Noise, AR(1), S-Plus, Estimation, and Simulation We begin with an exploration of the normal noise model, then we look at its simplest alternative, the AR(1) model. Stationarity: Logically the \whole banana" yet logically untestable (per the cycle construction) Statistics 434: Bullet Points for Day 8 ARIMA(p,d,q) In Full After considering the \stylized facts" suggested by HW3, we complete our description of the most widely used class of univariate time series models, the ARIMA(p,d,q) models. 3 and σ2 = 1. We also start to consider Statistics 434: Bullet Points for Day 15 Time Series Regression and the CAPM Chapter 6 of Zivot and Wang develops regression in the context of time series. There is also relevant code in the code box. If you are just now thinking about taking 434 next fall, you might want to jump down to a discription of the course prerequisites, etc. We’ve lost our major hold on “learning from the past. Review the ma-terial on writing S functions. Statistics 434: Bullet Points for Day 21 Co-integration and Statistical Arbitrage When one reasons about asset prices, there is a recurring tension between “trend following” and “mean reversion. We then use martingale Engle's GARCH 101 is closely related to his Noble Lecture though the Nobel Lecture has a few parts that will not be transparent to 434 students. 07 under the hypothesis of Statistics 434: Bullet Points for Day 16 Switching Regressions and Other Non-Linear Ideas for Forecasting Returns We’ll go over the Clive Grainger’s article “Forecasting stock market prices: Lessons for forecasters. ” So far, almost all of the tools that we have considered in our course have had more to say about the “trend following. We will need to develop an understanding of the stationarity of the AR(p) Statistics 434: Bullet Points for Day 21 Co-integration and Statistical Arbitrage When one reasons about asset prices, there is a recurring tension between “trend following” and “mean reversion. sim(). 3 %âãÏÓ 27 0 obj > endobj xref 27 58 0000000016 00000 n 0000001908 00000 n 0000001988 00000 n 0000002181 00000 n 0000002355 00000 n 0000002844 00000 n 0000003499 00000 n 0000003745 00000 n 0000021902 00000 n 0000022422 00000 n 0000022792 00000 n 0000023182 00000 n 0000023589 00000 n 0000023641 00000 n 0000037417 00000 n 0000037468 00000 n 0000037835 00000 n 0000039242 00000 n Still, I won't erase things either, so if you are thinking about taking Stat 434 in the Fall of 2007, what you find here should give you an honest impression of what the course is all about. This leads to a discussion of AR(p) vs EMH and the introduction of the important notion of a martingale. Now there is no one among us who is in anyway unwilling, so the title is a bit off putting. Reading † Review the material in Zivot and Wang on the creation of time series objects and the use of the timeDate() function. Statistics 434: Bullet Points for Day 15 Time Series Regression, CAPM, and the Three Factor Model For us, time series regressions are typified by the Capital Asset Pricing Model (CAPM) and the Fama French Three Factor Model (FF3FM). Mostly for Fun Links Statistics is required • I assume you have taken the following courses: – Derivative Securities – Continuous Time Finance – Scientific Computing / Computing for Finance • Programming in C/C++ or MATLAB/R is required 1. He's also organizing a campus event --- check it out: On November 26th and 27th, Citi’s University of Pennsylvania Alumni will be on campus to discuss careers in Sales & Trading. Plot your return series and the square of your return series Statistics 434: Bullet Points A Pre-Thanksgiving Interlude In the Wednesday afternoon before Thanksgiving, attendance typically runs under 60%, so the most practical to use of this time is to cover some special topics that one can miss without creating a gap in the core material everyone must know. After that, you might look at some of the 2008 e-Handouts or read at random (from the bottom) in the blog. If you are shopping now for courses for Fall 2010, you can get an idea of what our course will be like by reading from the bottom up. We start to consider when one model might be preferred to another based on the ACF or PACF plots. Statistics 434: Bullet Points for Day 7 AR(1), AR(2) and AR(p) We now consider the full suite of autoregressive models, beginning with a look at the most useful of these | the modest AR(2) model made famous by Yule’s study of sun spot data. Also, it's just in the nature of our course that the blog page will get loaded up with oodles of keywords. Stationarity: Logically the “whole banana” yet logically untestable (per the cycle construction) https://webcafe. I'll keep this page up for a little while, but before summer time it will disappear. One nds huge dependence in squared returns via Ljung-Box tests. Summary of monthly relative performance statistics during “bad times” over 1963–2006 sample Trailing U. One finds huge dependence in squared returns via Ljung-Box tests. The Capital Asset Pricing Model ( alias, CAPM) serves as our leading example. It is offered in the fall and does have the Statistics 434 Homework No. We will learn basic statistical concepts such as mean, variance, quantiles and hypothesis testing, and basic R programming for data management and The Teaching Assistant for Stat 434 is Dan McCarthy, who for the moment has email and a website. Statistics 434: Bullet Points for Day 13 Stationarity and Unit Root Tests If a time series is not stationary, or cannot be transformed to be stationary — say by taking differences, then we are pretty close to stuck. Statistics 434: Bullet Points for Day 7 AR(p) with p ≥ 2 We now consider the autoregressive models with p ≥ 2, beginning with a look at the most useful of these — the modest AR(2) model that was made famous by Yule’s study of sun spot data. On the other hand, Chapter 9 is quite useful for our purposes, and it is a chapter everyone should master | except for Section 9. Statistics 434: Bullet Points for Day 4 Autocorrelation in Theory, Practice, and Tests The first question that one must ask of a stationary time series is simply “Do I have any reason to believe that there is any dependence among these values, or do they behave like independent random variables?” Statistics 434: Bullet Points for Day 22 A Pre-Thanksgiving Interlude In the Wednesday afternoon before Thanksgiving, attendance typically runs under 60%, so the most practical to use of this time to cover some special topics that one can miss without creating a gap in the core material everyone must know. ) Homework Assignments (Fall 2005) Bullet Point Day Plans (Fall 2005) Software Tools . The obvious value of the ARCH/GARCH models opened a flood gate of variations. ” Graninger won the 2003 Bank of Sweden Prise in Honor of Alfred Nobel, and he has footprints all over financial econometrics. In particular, we consider the tools for simulation and for tting using the method of maximum likelihood. Reading Read Zivot and Wang pages 1{71, but skip Section 1. 3 Due Monday October 3. GARCH ZOO . Let me know how this design does --- or does not --- work for you. 2. Explore the effect (if Statistics 434: Bullet Points for Day 23 Co-integration and Statistical Arbitrage In the battle between \trend following" and \mean reversion" almost all of the tools that we have considered in our course have had more to say about the \trend following" argument. 2707 - Financial Econometrics and Statistical Arbitrage Lecture Market Microstructur Theory Oct 3, 2012 · Divya Krishnan took 434 in the Fall of 2008 (a tough year!) and now he is working in Sales and Trading at Citigroup. Do take The blog structure also facilitates SEO. g. ! Due Date Reminder: Noon 12:00, Wednesday December 16. You really must have understood your earlier statistics courses --- in addition to having done well in them. %PDF-1. Statistics 434: Bullet Points for Day 5 Autocorrelation Tests | Especially the Ljung-Box Test When is it feasible to treat a series of returns as if they are independent? In other words, when do returns behave like noise? This is one of the most basic questions that one can ask about a series of flnancial returns. Statistics 434: Bullet Points for Day 10 Bet Sizing and Long-term Wealth Growth Rates Today we take a little side tour from our investigation of the ARIMA(p,d,q) model to look at what the general question “Facing the possibility of a favorable bet, what fraction of one’s wealth should one bet?” This question leads us to Statistics 434 Homework No. upenn. This started an eleven -year process of deregulation that transformed pipeline companies from distributors into transporters and opened the door for competition among independent marketing and distribution companies. Statistics 434: Bullet Points for Day 14 Value at Risk, Extreme Values, Risk-Adjusted Returns Chapter 5 of Zivot and Wang discusses extreme value theory, and it also opens a conversation about risk. Like all one-page blogs, this one reads in reverse chronological order. 3 and just skim pages 19{40. 2 Due Monday September 26. A further bene t of Statistics 434: Bullet Points for Day 5 Autocorrelation Tests | Especially the Ljung-Box Test When is it feasible to treat a series of returns as if they are independent? In other words, when do returns behave like noise? This is one of the most basic questions that one can ask about a series of flnancial returns. We’ll also add to your tool kit by discussing the likelihood function and its major applications: Statistics 434: Bullet Points for Day 22 Comparing Asset Returns in the Context of Risks Any asset manger, asset class, or investment strategy will be judged on the basis of the historical returns viewed in the context of the risks that were taken | but how? There are oodles of suggestions, yet if we are honest, none of these Statistics 434: Homework No. Still, I won't erase things either, so if you are thinking about taking Stat 434 in the Fall of 2007, what you find here should give you an honest impression of what the course is all about. Simulation and Estimation of an AR(2) or ARIMA(2,0,0) process † Let `1 = 0:2, `2 = 0:15, and ¾ =:25. You should look on them as being more like STAT 0001 Introduction to Statistics and Data Science. ” Statistics 434: Bullet Points for Day 23 Co-integration and Statistical Arbitrage In the battle between “trend following” and “mean reversion” almost all of the tools that we have considered in our course have had more to say about the “trend following” argument. Code Box Index (Stat 434 Wharton) Some Guides to S-Plus . 6. Your real goal is to show that you have achieved a high level of skill and knowledge in the practical investigation of financial time series. Plot your return series and the square of your return series Risk Free Rate . This course introduces students to the time series methods and practices which are most relevant to the analysis of financial time series--- especially series of equity returns, interest rates, and exchange rates. Financial Time Series (Stat 434) Plan for Fall 2007. You should look on them as being more like Risk Free Rate . We will examine the CAPM in some detail, but for the moment the Statistics 434: Financial Time Series First Day Questionnaire Your Name and your E-Mail Address: Your School, Major, and Year of Study: How did you hear about this course? Friend? Advisor? Other? Something about yourself, such as where you grew up, or anything else that you would like me to know: Statistics 434: Bullet Points for Day 10 Bet Sizing, A Portfolio Limit Theorem, and Personal Utility This lecture takes a break from our investigation of the ARIMA(p,d,q) model and looks at what we might do with a model for asset returns if we were lucky enough to flnd a good one. Reading Read Chapter 9 of Z&W. The real pay dirt is on pages 15{19, pages 40{54, and pages 56{71. 702 The Journal of Finance single experiment, standard statistical theory indicates that the probability of observing a t statistic at least as large as 3. If you are thinking about taking Stat 434 in the Fall of 2007, I have a few tips and some practical information. Course Syllabus (Fall 2005) Course Policies (re: Missed Class, Teams, Homework Solutions, Etc. Simulated Portfolio Performance: AR(1) and the Kelly Principle Statistics 434: Bullet Points for Day 24 Risk Adjusted Returns It is a simple fact that any mutual fund, investment manger, asset class, or investment strategy will be judged on the basis of its historical returns. 8 Data Get four years’ (or a little less) of daily returns from CRSP for one of your favorite firms, or perhaps of some ragged mutual fund, or some interesting ETF. 4 on High frequency data; this can be skipped. 9 Reading Read the S-Plus Help files for all of the new S-Plus functions that we have covered and explore the help files for the “related functions” that are given at the bottom of the help files. mle, and arima. These outline are but faint shadows what we really cover. The Microsoft Example (a) S-Plus Speciflcation (and text typo) (b) New Statistics 434: Bullet Points for Day 9 Simulating and Fitting ARIMA(p,d,q) Models We examine the computation tools for studying the ARIMA(p,d,q) models. • Use the unitroot() function to find the p-values for the augmented Dickey Fuller tests applied to your price and return data. Statistics 434: Bullet Points for Day 17 Introduction to ARCH and GARCH The ARCH model is motivated by the an easily conflrmed empirical fact that for many assets the sequence of squares of asset returns show highly signiflcant autocorrelation. We’re skipping Chapter 8; the jury is out on its relevance. Still, it is perfectly OK to just read the juicy bits.