Time Series Analysis & Forecasting using Stata |
|
| Date: Location: Course duration: Software: Level: Delivered by: Course Code: |
9-12 July 2013 Subotnick Financial Services Centre, Zicklin School of Business, Baruch College, New York City, NY, USA 4-days Stata Introductory / Intermediate Prof. Robert A. Yaffe, New York University ST-135-USA |
 |
  |
Contents
- Course overview
- Agenda
- Who should attend
- Mathematical background required
- The principal lecturer
- Prices
- Registration
- Terms & Conditions
|
Back to top  |
 |
Course overview
This course is combined with the Introduction to Time Series Analysis using Stata course, allowing the 1-day introductory part of the course to be taken by course delegates separately to the core 4-day Time Series Analysis and Forecasting using Stata course.
The course assumes little mathematical background on the part of the participants. The course shows how to apply these techniques to real-life social science, economic, business, financial, and medical data, with many examples on the reporting and interpreting of the results. Participants are welcome to bring their own data.
|
Back to top |
|
Agenda
(Subject to minor changes)
Day 1
Morning Session
Basic Time Series Analysis Concepts
- Definition of a time series
- Cycles
- Trends
- Seasonality
- Lags, leads, differences
- Nomenclature
- Expectation notation
- Summation notation
Break
Time Series Setup with Stata
- Inputting time series data
- Time-date functions and applications
- Importing and exporting time series data
- Graphing Time Series with Stata
- Preliminary analysis of time series with Stata
Lunch
Afternoon Session
Stationarity
- Covariance stationarity
- Strict stationarity
- Dickey Fuller tests
- theory
- programming dfuller tests
- Augmented Dickey-Fuller tests
- theory
- programming
- Phillips-Perron tests
Autocorrelation
- Theory
- Types
- Characteristic ACF and PACF patterns
- Programming the correlograms
- Box-Ljung significance tests
Break
Moving averages
- Theory
- Types
- Characteristic ACF and PACF patterns
- Programming the ACF and PACF
- White noise Significance tests
Hands-on Experience and Programming practice
- Stationarity diagnosis and transformations
- ARIMA identification
- Integrated processes
- AR processes
- MA processes
- ARMA processes
Day 2
Morning Session
ARIMA modeling
- Estimation
- Estimation algorithms
- full maximum likelihood
- conditional maximum likelihood
- Diagnosis
- Intervention modeling
- Model fitting
Break
Seasonal ARIMA models
- Identification
- Estimation
- Diagnosis
- Model fitting
Lunch
Afternoon Session
Forecasting theory
- sample segmentation
- segment lengths
- in-sample v. post-sample forecasting
- point forecasts
- interval forecasts
- forecast profiles
- out-of-sample forecasts
- ex ante forecasts
- one-step ahead forecasts
- dynamic forecasts
- structural forecasts
- combining forecasts
Break
Forecasting Evaluation
- Tests of forecast bias
- Tests of forecast accuracy: out-of-sample and ex-ante
- MSFE
- MAE
- MAPE
- MdAPE
- Theil?s U
- Diebold-Mariano test of comparative forecast evaluation
Forecasting Graphics
Hands on ARIMA modeling and forecasting
Day 3
Morning Session
Intervention (Impact) Analysis
- Pulse interventions
- Level Shifts
- Testing for them
Break
Outliers
- Additive
- Periodic Pulses
- Innovational
- Patches
- Modeling outliers
Intervention modeling with Arimacheck
Hands-on programming
Lunch
Afternoon Session
Dynamic Regression Models with Stata
- Impulse Response functions
- deterministic inputs
- stochastic inputs
- Dynamic Regression Analysis Linear Transfer Function methodology
- Dynamic Regression modeling with arimacheck
- Forecasting with Dynamic Regression Models
- out-of-sample
- ex ante
Break
Cointegration
- exogeneity
- Granger causality
- Tests for exogeneity
- Error Correction models
Q and A
Day 4
Morning Session
Autoregressive Error Models
- First order correction theory: Cochran-Orcutt
- Prais-winston models
- Newey-west robust models
- Regression diagnostics
- Autocorrelation tests
- Heteroskedasticity tests
- Parameter constancy tests
Q and A
Hands-on programming
Robust time series analysis
- Semi-robust time series analysis
- Robust time series models
- Robust time series with arimacheck
Lunch
GARCH models: Theory and programming
- ARCH
- Forecasting with ARCH
- GARCH
- Forecasting with GARCH
- Forecast Evaluation with GARCH Forecasts
Out-of-sample
- ex ante
- EGARCH
- modeling leverage effects
- Volatility smiles and skews
- Graphing
- Modeling
- GJR Threshold GARCH
- APGARCH
Break
Recapitulation
Q and A
Hands-on programming
Subjects to be covered if time permits
Vector Autoregression
- Definition
- Assumptions
- Tests for assumptions
- Estimation
- Forecasting
- Structural VAR
- Orthogonal impulse response functions
- Forecast error variance decomposition
- Constraints
- Varbasic, var, and svar programming
|
Back to top |
|
Who should attend
The course, given in English, is aimed at students, researchers, and forecasters interested in:
- Basic Stata
- Basic cross-sectional statistics with Stata
- Longitudinal analysis with Stata
- Box-Jenkins Time Series Analysis with Stata
- Seasonal Box-Jenkins Models
- Forecasting with time series models
- Outlier modeling
- Dynamic regression analysis with Stata
- GARCH modeling with Stata
- Forecasting evaluation
- Policy and impact analysis wih Stata
- Financial risk analysis with Stata
|
Back to top |
|
Mathematical background required
- High School Algebra
- Basic Statistics
|
Back to top |
|
The principal lecturer
Robert A. Yaffee, Ph.D., is currently a research scientist/research professor at the Silver School of Social Work and a senior research scientist/statistician on National Science Foundation grant # 0826983 to study the psychological sequelae of the Chernobyl accident in collaboration with co-principal investigors at the University of Colorado, Colorado State University, and at the Academy of Labor and Social Relations, Federation of Trade Unions, in Kiev, Ukraine. Dr. Yaffee is currently working on several longitudinal research projects. These projects entail panel data analysis, event history analysis, time series analysis, state space models, Bayesian disease mapping and risk analysis. Yaffee has taught short courses on introductory, intermediate, and advanced time series analysis, volatility analysis, and forecasting. Dr. Yaffee is the author of a variety of articles reviewing statistical packages and is currently writing about applied time series analysis and forecasting.
|
Back to top |
|
Prices
Cost (per participant):
| Price |
| Commercial / Government | $2800.00 | |
|
||
|
||
| Commercial / Government - Attend all 5-days (Includes attendance at Introduction to Time Series Analysis) |
$3500.00 | |
|
||
|
||
| Academic / Non-profit research | $2100.00 | |
|
||
| Academic / Non-profit research - Attend all 5 days | $2625.00 | |
|
||
| Student Registrations | $1100.00 | |
|
||
| Student Registrations - Attend all 5 days | $1375.00 | |
|
||
- A 20% discount is applied to early registrations (registrations made more than 6 weeks in advance of the course start date)
- All costs exclude local taxes, where applicable
- Late Registrations: Registrations made within 6-weeks before the start of the course
- Student registrations: Attendees must provide proof of full time student status at the time of booking to qualify for student registration rate (valid student ID card or authorised letter of enrollment)
- Additional discounts are available for multiple registrations
- Cost includes course materials, lunch, refreshments and the use of computers (please advise us if you have any dietary requirements)
The number of delegates is restricted. Please register early to guarantee your place.
If you need assistance in locating hotel accommodation in the region, please notify us at at the time of booking.
|
Back to top |
|
Registration
We welcome delegates to find out more and register for the course by contacting our sales and training team either by email: info@timberlake-consultancy.com, phone: +1 908 686 1251 or by filling out an online registration form.
|
Back to top |
|
Terms & Conditions
Payment of course fees required prior to the course start date.
Registration closes 5-calendar days prior to the start of the course.
- 100% fee returned for cancellations made over 28-calendar days prior to start of the course
- 50% fee returned for cancellations made 14-calendar days prior to the start of the course
- No fee returned for cancellations made less than 14-calendar days prior to the start of the course
|
Back to top |
Return to: Training Calendar | Home |
