Location: NY, USA

The Course - The course assumes little mathematical background on the part of the participants. It teaches theory, modeling, programming, and interpretation of the major time series models, along with interesting applications to business and risk analysis in finance on a Windows based platform. 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.

Who should attend - The course, given in English, is aimed at students, researchers, and forecasters interested in

* Longitudinal analysis with Stata
* Box-Jenkins Time Series Analysis with Stata
* Seasonal Box-Jenkins Models
* Outlier modeling
* Dynamic Regression Analysis with Stata
* GARCH modeling with Stata
* Forecasting with time series models
* Forecasting evaluation
* Policy and Impact Analysis with Stata
* Financial Risk Analysis with Stata

Mathematical Background Required

* High School Algebra
* Basic Statistics

Helpful but not required background

* Linear or Matrix Algebra
* Basic differential and integral calculus

Advantages - The course will

* Provide an Introduction to Applied Time Series Analysis Theory, Modeling, and Forecasting with Stata
* Review major Time Series Analysis and Forecasting Theory including Box-Jenkins ARIMA, Time Series Regression, and GARCH Modeling
* Provide hands-on experience in time series analysis and forecasting models - each delegate is provided with a computer throughout the course

The Principal Lecturer – Dr Robert A. Yaffee.

Agenda

Day 1 Morning
8:30am coffee and Registration


9:00
1. Basic Time Series Analysis Concepts

* definition of a time series
* cycles
* trends
* seasonality
* lags, leads, differences
* nomenclature
* Expectation notation
* Summation notation

10:30 Break

2. 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

12:00 noon-1:30pm lunch
3. Stationarity

* covariance stationarity
* strict stationarity
* Dickey Fuller tests
* theory
* programming dfuller tests
* Augmented Dickey-Fuller tests
* theory
* programming
* Phillips-Perron tests

4. Autocorrelation

* Theory
* Types
* Characteristic ACF and PACF patterns
* Programming the correlograms
* Box-Ljung significance tests

2:30-2:45pm Break

5. Moving averages

* Theory
* Types
* Characteristic ACF and PACF patterns
* Programming the ACF and PACF
* White noise Significance tests

6. Hands-On Experience and Programming practice

* Stationarity diagnosis and transformations
* ARIMA identification
* Integrated processes
* AR processes
* MA processes
* ARMA processes

Day 2 Session begins at 9:00am
1. ARIMA modeling

* estimation
* estimation algorithms
* full maximum likelihood
* conditional maximum likelihood
* diagnosis
* Intervention modeling
* model fitting

Break 10:30
2. Seasonal ARIMA models

* dentification
* Estimation
* diagnosis
* model fitting

Lunch 12:00-1:30
Afternoon 1:30-2:30
3. 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

2:30-2.45 PM Break
4. 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

5. Forecasting Graphics

6. 3:00- 5:30 Hands on ARIMA modeling and forecasting

Day 3 Session begins at 9:00am
1. Intervention (Impact) Analysis

* Pulse interventions
* Level Shifts
* Testing for them

2. Outliers

* Additive
* Periodic Pulses
* Innovational
* Patches
* Modeling outliers

3. Intervention modeling with Arimacheck

4. Hands-on programming

Lunch: 12-1:30pm

5. Dynamic Regression/Impulse response analysis

* Dynamic Regression Models with Stata
* Impulse Response functions
* deterministic inputs
* stochastic inputs
* Dynamic regression analysis/multiplier assessments.
* Dynamic Regression modeling with arimacheck
* Forecasting with Dynamic Regression Models
* ut-of-sample
* ex ante

Break 2:30-2:45pm
6. Cointegration

* exogeneity
* Granger causality
* Tests for exogeneity
* Error Correction models

4:00-5:00pm
Q and A Hands on

Day 4: Session begins at 9:00am
1. 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

10:30-10:45 Break

2. Q and A

3. Hands-on programming

4. Robust time series analysis

* semi-robust time series analysis
* robust time series models
* robust time series with arimacheck

12:00-1:30pm Lunch
5. GARCH models: Theory and programming

* ARCH
* Forecasting with ARCH
* GARCH
* Forecasting with GARCH
* Forecast Evaluation with GARCH Forecasts
o out-of-sample
o ex ante
* EGARCH
o modeling leverage effects
* Volatility smiles and skews
* graphing
* modeling
* GJR Threshold GARCH
* APGARCH


Break: 2:30-2:45

5. Recapitulation


6. Q and A


7. Hands-on programming


4:30PM – end

http://www.timberlake.co.uk/training...ataTSUSA1.html