Thursday 9 May 2013

Introduction to Structural Equation Modeling


Many statistical methods were "invented" long ago, but laid around idle, waiting for computers to empower them.  Structural equation modeling (SEM), (and its subsidiary concept of "latent constructs" that can't be measured directly), is one.  Statistics.com's SEM courses are taught by Prof. Randall Schumacker, a leader in the field. "Introduction to Structural Equation Modeling" is offered at statistics.com. For more details please visit at http://www.statistics.com/sem.

Structural Equation Modeling (SEM) is a general statistical modeling technique to establish relationships among variables.  A key feature of SEM is that observed variables are understood to represent a small number of "latent constructs" that cannot be directly measured, only inferred from the observed measured variables.  This course covers the theory of SEM, and practical work with computer software and real data.  It covers the key concepts in SEM - at the conclusion of the course students will be able to specify different forms of models, using observed, latent, dependent and independent variables. Student will be able to conduct confirmatory factor analysis, and diagram SEM models.

Who can take this course?
Market researchers, educational researchers, sociologists and psychologists, political scientists, economists, and survey researchers.

Course Program:

Course outline: The course is structured as follows

 

SESSION 1: Preliminaries

  • LISREL software installation
  • PRELIS
  • Data entry and Data Edit issues
  • Correlation and Covariance Data Files

SESSION 2: Modeling

  • SEM Basics
  • Regression models
  • Diagramming Models
  • Path Analysis Models

SESSION 3: Measurement Models

  • Exploratory vs. Confirmatory factor analysis
  • Latent Variables
  • CFA models


SESSION 4: Developing Structural Equation Models

  • Combining Path and Factor Models
  • 5 Basic SEM steps
    • Model Specification
    • Model Identification
    • Model Estimation
    • Model Testing
    • Model Modification
  • Amos Audio/Video Presentation

Instructor, Dr. Randall E. Schumacker, is Professor in Educational Research at the University of Alabama. Dr. Schumacker was the founder, editor (1994-1998), and is the current emeritus editor of Structural Equation Modeling: A Multidisciplinary Journal. He also founded the Structural Equation Modeling Special Interest Group at the American Educational Research Association.

You will be able to ask questions and exchange comments with the instructors via a private discussion board throughout the course.   The courses take place online at statistics.com in a series of 4 weekly lessons and assignments, and require about 15 hours/week.  Participate at your own convenience; there are no set times when you must be online. You have the flexibility to work a bit every day, if that is your preference, or concentrate your work in just a couple of days.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune (www.c-elt.com).

For India Registration and pricing, please visit us at www.india.statistics.com.

Call: 020 66009116

Websites:

Regression Analysis


The origin of the term "regression" dates from Francis Galton's work with sweet pea seeds, and Karl Pearson's biography of Galton. At the Institute for Statistics Education, "Regression Analysis" is your bridge between introductory level courses and more advanced courses.

Dr. Iain Pardoe will present his course "Regression Analysis," online at statistics.com. "Regression Analysis" covers simple and multiple linear regression, standard assumptions and how to check them, what to do when they are not appropriate, diagnostics for residuals and influential observations, transformations, multicollinearity, auto-correlation, variable selection and more. For more details please visit at http://www.statistics.com/regression/.

Who Should Take This Course:
Scientists, business analysts, engineers and researchers who need to model relationships in data in which a single response variable depends on multiple predictor variables.

Course Program:

Course outline: The course is structured as follows
SESSION 1: Foundations and Simple Linear Regression
  • Brief review of univariate statistical ideas:
    • confidence intervals
    • hypothesis testing
    • prediction
  • Simple linear regression model and least squares estimation
  • Model evaluation:
    • regression standard error
    • R-squared
    • testing the slope
  • Checking model assumptions
  • Estimation and prediction

SESSION 2: Multiple Linear Regression
  • Multiple linear regression model and least squares estimation
  • Model evaluation:
    • regression standard error
    • R-squared
    • testing the regression parameters globally
    • testing the regression parameters in subsets
    • testing the regression parameters individually
  • Checking model assumptions
  • Estimation and prediction

SESSION 3: Model Building I
  • Predictor transformations
  • Response transformations
  • Predictor interactions
  • Qualitative predictors and the use of indicator variables

SESSION 4: Model Building II
  • Influential points (outliers and leverage)
  • Autocorrelation
  • Multicollinearity
  • Excluding important predictors
  • Overfitting
  • Extrapolation
  • Missing data
  • Model building guidelines
  • Model interpretation using graphics

The instructor, Iain Pardoe, is the author of "Applied Regression Modeling: A Business Approach" (Wiley). If you are following the Oscars, check out his paper in the Journal of the Royal Statistical Society on predicting Academy Award winners. (http://www.iainpardoe.com/oscars.htm)

This course takes place over the internet at the Institute for 4 weeks. During each course week, you participate at times of your own choosing - there are no set times when you must be online. The course typically requires 15 hours per week. Course participants will be given access to a private discussion board so that they will be able to ask questions and exchange comments with instructor, Dr. Iain Pardoe. The class discussions led by the instructor, you can post questions, seek clarification, and interact with your fellow students and the instructor.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune.

For India Registration and pricing, please visit us at www.india.statistics.com.

Call: 020 66009116

Websites:

Financial Risk Modeling

Some time ago, Facebook announced that it would acquire Instagram, a photo sharing service, for $1 billion.  Facebook's analysis (its shareholders must hope) would have generated a range of potential valuations and how likely they were, factoring in uncertainties about how fast the user base will grow, how fast photo uploads will grow, what the advertising volume will be, how advertising can be priced, and more.

Estimates like this are arrived at via risk simulation to attach probabilities to sequences of potential outcomes and values.  Learn how to conduct and analyze such simulations in Huybert Groenendaal's "Financial Risk Modeling," an online course at Statistics.com.

In addition to discussions of recent innovations in the application of Monte Carlo methods, the course will cover many practical examples, case studies and interactive sessions. Finally, the course will also cover common mistakes and how to avoid them.  The software used is ModelRisk, an Excel add-in; a license will be provided for the duration of the course. For more details please visit at
http://www.statistics.com/financialrisk.

Aim of Course:
This course will cover the most important principles, techniques and tools in Financial Quantitative Risk Analysis. The course has been developed to effectively combine theoretical sessions with classroom examples and exercises in order to provide students with a comprehensive analysis of Monte Carlo techniques. In addition to discussions of recent innovations in the application of Monte Carlo methods, the course will cover many practical examples, case studies and interactive sessions.

The course will also get the participants comfortable with risk analysis modeling environments (in this case ModelRisk with the Insurance and Finance Module within Excel, but the lessons and techniques apply equally well to other modeling environments).

Who can take this course:
Anyone in investment banking, asset / investment / fund management, merchant banking, insurance companies, software / technology, government/public body and academia with an interest in applying quantitative probabilistic techniques in the fields of finance and insurance.

Course Program:

Course outline: The course is structured as follows

SESSION 1: Introduction
  • Introduction to quantitative risk analysis and Monte Carlo
    • Core ideas of risk analysis
    • What is a probability distribution
    • How scenarios are generated, outputs produced and analyzed, why it works
  • Distributions
    • Most common univariate distributions in finance
    • Introduction to statistical descriptors-mean,mode,standard deviation,skewness,kurtosis
    • Example financial model and exercise
SESSION 2: Stochastic Time Series
  • Trend, volatility, seasonality, autocorrelaton, cyclicity, mean reversion
  • GBM, +mean reversion, jump diffusioin, both, seasonality
  • Autoregressive models: ARCH, GARCH, EGARCH, APARCH
  • Markov chains
  • Multi-variate time series
  • Discussion of attributes and application of different stochastic time series
  • Example model and exercise

SESSION 3: How to Deal with Correlations
  • Rank order
  • Covariance measures
  • Copulas
  • Example model and exercise
SESSION 4: Model Fitting and Conclusion
  • Fitting distributions, time series and copulas to historical data
    • Distributions (MLE)
    • Time series (MLE)
    • Copulas (MLE)
    • Fit comparisons with information criteria (i.e. AIC, SIC, HQIC)
    • Example model and exercise
  • Emphasis on examples model and practical case
    • VAR, expected shortfall examples
    • Some time series examples (including fitting to past financial datasets)
    • Analyzing correlations between stochastic variables, fitting copulas and applying then in a simulation model
    • Basel II example with operational risk
    • Markov Chain model example (for modeling credit portfolios)

Huybert Groenendaal is a Managing Partner at EpiX Analytics, which specializes in risk analysis and modeling techniques for clients around the world.  He consults on a broad range of projects that include forecasting, financial risk analysis, project costs estimation, valuation, portfolio evaluation in fields such as pharmaco-economics, epidemiology, inventory optimization, mining and transportation. Dr. Groenendaal teaches risk analysis in the executive MBA program at the Leeds School of Business, University of Colorado at Denver and at the school of Management at the University of Texas at Dallas.

Greg Nolder is a risk analyst with experience in computer hardware, pharmaceuticals, banking, finance, construction, mining, oil & gas, chemicals, consumer packaged goods, transportation and engineering. Of particular interest are systems involving stochastic optimization, general QRA and applying analytics to amateur and professional sports.

You will be able to ask questions and exchange comments with the instructors via a private discussion board throughout the course.   The courses take place online at statistics.com in a series of 4 weekly lessons and assignments, and require about 15 hours/week.  Participate at your own convenience; there are no set times when you must be online. You have the flexibility to work a bit every day, if that is your preference, or concentrate your work in just a couple of days.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune (www.c-elt.com).

For India Registration and pricing, please visit us at www.india.statistics.com.

Call: 020 66009116

Websites:

R Programming – Advanced


Do you like to study key concepts for writing advanced R code, emphasizing the design of functional and efficient code?  Join Dr. Oliva C. Lau in her online course R Programming – Advanced at Statistics.com, it will set students down the road to mastering the intricacies of R.  After completing the course, students should be able to read, understand, modify, and create complex functions to perform a variety of tasks. For more details please visit http://www.statistics.com/r-program-adv/.

Who Should Take This Course:
To get the most out of this course, you should have several years' experience programming in R already: you should be familiar with writing functions, and the basic data structures of R (vectors, matrices, arrays, lists and data frames).

Course Program:
SESSION 1: Functions
  • Environments
  • Creating user-defined functions

SESSION 2: Evaluation
  • Creating a function call
  • Delayed function execution

SESSION 3: Functions within functions
  • Lexical scoping
  • Search path

SESSION 4: Classes
  • Types of classes
  • Generic functions
  • Writing user-defined classes

Instructor, Dr. Oliva C. Lau is a self-described R ninja with over 10 years of experience with applied statistics and statistical software development in R. Throughout her varied work experience in regulatory drug development, Silicon Valley high tech, and the federal sector, she has focused on client-centric problem-solving.

This course takes place over the internet at the Institute for 4 weeks. During each course week, you participate at times of your own choosing - there are no set times when you must be online. The course typically requires 15 hours per week. Course participants will be given access to a private discussion board so that they will be able to ask questions and exchange comments with instructor, Dr. Oliva C. Lau. The class discussions led by the instructor, you can post questions, seek clarification, and interact with your fellow students and the instructor.

For Indian participants statistics.com accepts registration for its courses at special prices in Indian Rupees through its partner, the Center for eLearning and Training (C-eLT), Pune.

For India Registration and pricing, please visit us at www.india.statistics.com.

Call: 020 66009116

Websites: