 |
 |
 |
 |
 |
 |
|
Applied Statistics for Financial Investment Analysis
February 12, 2010
February 20, 2010
March 27, 2010
April 23, 2010
May 8, 2010
Subotnick Financial Services Centre, Zicklin School of Business, Baruch College/CUNY
Information and Technology Building, 151 E. 25th Street. New York, NY 10010, U.S.A.
Contents
Course Description
Course Programme
Request an Enrolment Form Now
Terms and Conditions
Investors, traders and risk managers must have a solid grasp on the statistical distributions of returns and risk factors, and their possible interactions and changes over time.
Making sense of time series data requires appropriate statistical tools - and the objective of this series of 1-day workshops, starting in September 2009, is to make you comfortable with the methods required to conduct empirical time series analysis for decision taking and forecasting.
The first in this series of five 1-day workshops provides participants with a high-level overview of major topics, illustrating the capabilities of modern techniques to perform powerful financial time series analysis, while becoming aware of modelling pitfalls and the limitations of simple (simplistic) models
During the subsequent 1-day workshops, participants will learn the concepts underlying the main modelling approaches and diagnostic tools to measure risk, analyze and forecast financial time series by way of illustrations
and through hands-on immersion in realistic case studies, applying user-friendly Excel and OxMetricsTM software.
Who should attend: Students of finance, financial analysts and investment professionals and other finance practitioners are regular users of statistical concepts - whether as readers/consumers or as analysts/producers of reports.
This interactive training course is designed for finance students and practitioners with a background in basic statistical principles, basic finance and little or no experience in Excel. The course benefits all those who need to enhance their ability to understand and carry out financial and risk analysis in Excel: commercial and investment bankers, regulators, traders, treasury and investment professionals, and market and credit risk analysts.
Advantages
Handbook, and all models, templates and add-ins are free for participants.
- Develop confidence in modelling financial data while gaining an appreciation of the consequences of using simple rules of thumb.
- Explore the use of linear regression models for describing causality between financial data, including hypothesis tests
- Understand the strengths, complexities and weaknesses of explicitly dynamic models, including those dealing with time-varying volatility
- Learn simulation and bootstrapping techniques to generate complex distributions of future prices (to value options), present values (NPV distributions), risk (value-at-risk), and to optimise using probability distributions of choice variables rather than single values
- Discover how asymmetry and 'fat tails' are estimated when dealing with performance measures, especially for hedge funds, and for market and credit risk
The Principal Lecturer: Dr. Frank Leiber: Frank is a skilled valuation and financial risk management expert, having specialized throughout his career on derivatives, credit and market risk, with practical experience gained in securitization and issuing structured notes as an investment banker. He serves as President of Leiber Associates Inc, a capital markets-consulting firm; and he is associated with CREVAL, a commercial real estate risk and valuation service provider for institutional investors, and with Geo Genesis Group, an emerging markets advisory and investment company. He is adjunct professor of finance at NYU, and he has widely lectured at other universities, financial institutions and for professional risk management associations (GARP and PRMIA).
Frank earned his PHD in financial econometrics from the Graduate Institute of International Studies at the University of Geneva
The course fees are: The cost includes course materials (handbook, all models, templates and add-ins), as well as complimentary lunch, refreshments and the use of computers. The number of delegates is restricted. Please register early to guarantee your place.
Further instructions will be sent with the joining instructions. If you need assistance in locating hotel accommodation in the area, request the help of our Training Department.
Cost - The course fees are
|
Prices
|
1 day course only | 5 day course |
| Professional |
$500
|
$2475
|
| Student |
$400
|
$1857
|
More discounts available:
- 10% discount per added participant from same or different institution
- 5% discount for early registrations (registrations done at least 1calendar month prior to the start of the course).
- 10% additional discount on 5-module series for participants in the 1-day seminar (September 25, 2009)
Financial applications and illustrations in Excel:
- Analyse sample returns series through descriptive statistics
- Estimate parameters of simple models to forecast returns
- Simulate price series to value options
- Bootstrap return series to measure value-at-risk
Course Summary:
Setting the stage
- Cross-section and time-series methods
The distributional characteristics of samples: random variables and financial time series
- Measures of central tendency, variability, shape and linear association
- Depicting frequency distributions, histograms and scatter plots
Several important distributions and their uses in finance
- Uniform, normal, exponential, beta, chi-square, binomial, Poisson
Making inferences
- Estimating population means and variances
- Testing hypotheses
- Testing hypotheses about population means, variances
- Type II errors, ROC and Power curves
DAY 1 – September 25th
|
8:30-9:00 |
Registration |
|
9:00-10:30 |
Setting the stage: Financial time-series and models |
|
|
Unconditional distributional characteristics financial time series |
|
|
Depicting densities and measuring central tendency, variability, shape and linear association |
|
10:30-10:45 |
BREAK |
|
10:45-12:15 |
Several important distributions and their uses in finance |
|
|
Uniform, normal, exponential, beta, chi-square, binomial, Poisson |
|
Making inferences and testing hypotheses |
|
|
|
Estimating population means and variance; Testing hypotheses about population means, variances; Type II errors, ROC and Power curves |
|
12:15-13:15 |
LUNCH |
| 1:15-3:00 |
The linear regression approach vs. models of dynamic variables |
|
Review and illustrate the assumptions, properties and limitations of the classical least squares estimators |
|
|
Overview and illustrate models for stationary and non-stationary time series |
|
| 3:00-3:15 | BREAK |
|
3:15-5:00 |
Simulation, bootstrapping and stochastic optimization |
|
|
Reveal and explain techniques using statistical distributions instead of fixed numbers |
Financial applications and illustrations:
- Analyse sample returns series through descriptive statistics
- Estimate parameters of simple models to forecast returns
- Simulate price series to value options
- Bootstrap return series to measure value-at-risk
DAY 2 – date to be determined
| 8:30-9:00 |
Registration |
| 9:00-10:30 |
Setting the stage: Correlation vs. causality |
|
The simple linear regression model: the bivariate case |
|
|
Assumptions of the ordinary least squares model, and properties of the OLS estimators |
|
|
Standard errors of the OLS parameters |
|
| 10:30-10:45 |
Break |
| 10:45-12:15 | Inference in the simple linear regression model |
| Infer likely population values based on the estimated regression parameters | |
| Hypothesis tests: significance, confidence intervals and the 't-test', the 'p-value' | |
| 12:15 - 1:15 | Lunch |
| 1:15 - 3:00 | More on the general linear regression model: the multivariate case |
| F-test, 'goodness-of-fit' statistic | |
| 3:00-3:15 | Break |
| 3:15-5:00 | The general linear regression model: the multivariate case |
| Diagnostic tests on model assumptions, functional form, multicolinearity, dynamic models | |
| Testing residuals for nonconstant variance, deviation from normality, parameter instability, autocorrelation |
Financial applications and illustrations
- Explain the returns of a REIT by estimating and interpreting the influence of a single factor (beta): the CAPM model
- Compute an optimal hedge ratio
- Jensen's alpha: 'Can you beat the market?'
- Explain the returns of a stock by estimating and interpreting the influence of multiple factors: the APT model
- Explain the valuation of properties by estimating and interpreting the influence of multiple characteristics: the hedonic model
- Determinants of sovereign credit ratings
DAY 3 – date to be determined
| 8:30-9:00 | Registration |
| 9:00-10:30 | Setting this Stage |
| Structural and time-series models | |
| The distributional characteristics of financial time series | |
| Describing and depicting explicitly dynamic univariate time series data | |
| 10:30-10:45 | Break |
| 10:45-12:15 | Stationary time series |
| Stationarity, autocorrelation, partial autocorrelation | |
| Auto-regressive and moving-average time series models | |
| 12:15-1:15 | Lunch |
| 1:15-3:00 | Nonstationary time series |
| Testing for unit roots, estimating integrated time series | |
| 3:00-3:15 | Break |
| 3:13-5:00 | Nonlinear AR()series |
| ARCH and GARCH models |
Financial applications and illustrations:
- Analyse sample return series through descriptive statistics
- Estimate parameters of simple AR and MA models to forecast returns
- Estimate parameters of simple ARIMA models to forecast returns
- Estimate parameters of univariate ARCH and GARCH models to forecast returns
DAY 4 - date to be determined
| 8:30-9:00 | Registration |
| 9:00-10:30 | Setting the stage |
| Generating time series based on assumed/estimated parameters | |
| Stochastic processes: simulating financial time series | |
| Whitle noise, random walks and mean-reversion models | |
| Choleski decomposition; simulation vs. bootstrapping | |
| 10:30-10:45 | Break |
| 10:45-12:15 | Constrained optimization |
| Analytic vs. simulation results of portfolio optimization | |
| 12:15-1:15 | Lunch |
| 1:15-3:00 | Simulated time series and valuation |
| NPV and IRR: deterministic cash flows and risk premium | |
| Sensitivity, scenario and simulation analysis: valuation with probabilistic cash flows | |
| 3:15-5:00 | Stochastic Optimization |
| Optimize an objective function, under certain constraints and using distribution functions instead of uncertain Values |
Financial applications and illustrations in Excel:
- Simulating risky returns and future value distributions of single time series
- Simulate price series to value option
- Simulate correlated series, portfolio VaR
- Single period portfolio allocation, subject to risk aversion
- Multiperiod portfolio with sustainable retirement withdrawal rate
- Deterministic valuation of a commercial property: DCF model with risk premium as estimated by CAPM
- Simulating risky returns and present value distributions of single time series
- Optimal pay-out structure for differentiated capital partners
DAY 5 - date to be determined
| 8:30-9:00 | Registration |
| 9:00-10:30 | Setting the stage: |
| Market risk: effects of deviations from the normal distribution | |
| A second look at the distributional characteristics of return samples | |
| Asymmetry, fat tails and quantiles; stable distributions | |
| 10:30-10:45 | Break |
| 10:45-12:15 | Joint probability distributions and correlation |
| Marginal and joint distributions; going beyond correlation (copulas) | |
| 12:15-1:15 | Lunch |
| 1:15-3:00 | Estimation methods |
| Fitting and comparing distributions; hypothesis tests and testing 'goodness-of-fit' | |
| Type II errors, ROC and Power curves | |
| 3:00-3:15 | Break |
| 3:15-5:00 | Stochastic processes and credit risk |
| The building blocks of jump-diffusion processes: Brownian motion and Poisson process |
Financial applications and illustrations:
- Analyse sample returns series through descriptive statistics
- Value-at-Risk, Conditional Value-at-Risk
- Measuring risk and performance in portfolios; the sqrt(horizon) rule
- Optimizing portfolios with different risk measures
- The quality of rating agencies' default prediction models
- Introduction to structural and reduced-form models for credit risk
Registration closes 14 calendar days prior to the start of the course.
Cancellations:
- full fee returned for cancellations made over 28 calendar days prior to start of the course
- half-fee returned for cancellations made 14 calendar days prior to he start of the course
- no fee returned for cancellations made less than 14 calendar days prior to the start of the course.
Payment of course fees required prior to the course start date
|
||