:: Live Web Training
Risk and Decision Assessment using @RISK, Part I
Risk and Decision Assessment using @RISK, Part II
Free Live Webcasts
Value Optimization in
a World of Choices
How do I deal with Multicollinearity using StatTools? — O.K.
If you recall, a regression equation indicates the effect of explanatory variables on the response variables, provided that the other variables in the equation remain constant. Another way of stating this is that the coefficient represents the effect of this explanatory variable on the response variable in addition to the effects of the other variables in the equation. Therefore, the relationship between an explanatory variable X and the response variable Y depends on which other X's are included or not included in the equation.
This is especially true when there is a linear relationship between two or more explanatory variables, in which case we have multicollinearity.
At Pantektor, @RISK Responds to Fire Safety
Safety management is an essential element in averting disaster in the event of fire. Although the majority of premises will never have a serious fire, the consequences of such an event are so severe that it is critical that fire safety procedures are rigorously planned for. Managing fire safety begins with the initial design of a building but also includes safety systems and plans to minimize damage.
Palisade Software in Agriculture
Agriculture is one industry where the business selling the product doesn’t set the price point. Prices result from a complex set of factors that include weather, government, and international trade. Small wonder, then, that corporate farmers, the consultants who advise them, and agricultural economists often turn to Palisade software to get a more accurate fix on agricultural prices and farm income.
:: Anticipating Prices
In Australia, for example, wool is crucial to the national economy, and vast amounts of it are sold in individual lots via auctions across the country. Both wool producers and buyers want to know what to expect at auction time. Wool comes in so many different types and “sizes,” that sales information from the auctions amounts to vast datasets. Taking advantage of all this information, one industry analyst uses NeuralTools to work through the huge volume of sales data and to model the prices that can be anticipated for various types of wool at particular auction locations. NeuralTools “learns” pricing patterns on a limited set of the data, applies these patterns to a much larger dataset, and generates numerical predictions for the prices of various types of wool. With each addition of new sales data, the NeuralTools network becomes denser and more sophisticated, and its predictions more accurate.
:: Predicting Farm Income
In South America, large family-held farm corporations use @RISK to help them plan their crop operations for each year. Borrowing a strategy from investment advisers who create portfolios of stocks and bonds to manage risk and opportunities, these businesses use @RISK to create similar analyses of their farming operations. They use inputs for weather, type of crop, planting technique, land costs, and historical price data, to model the yield and return across their entire “portfolio” of farming operations. The @RISK models guide their decisions on how much land in which areas to farm, what to plant, and the amount of income to expect.
In the U.S., government programs are a supplementary source of income for farmers and are used to both reduce farming risk and enhance its rewards. Some programs provide price protection, others give a direct subsidy, and still others subsidize the purchase of crop insurance. Which of these schemes is most effective? Economic researchers at Purdue and Cornell used @RISK to model the effects of a number of individual programs on farm income and then to simulate the outcomes if all the programs were combined. The @RISK results demonstrated that crop insurance subsidies would be most effective, but even more important, the simulations revealed how the programs interact with each other.
:: Expanding Simple Models
One thing these examples from agriculture make clear is the capacity of the Palisade tools for easy expansion and refinement. The users have started with simple models and added information until the resulting models accurately reflect the complex forces at work throughout the agricultural markets.
2007 User Conference North America continued from above
Beautiful, sunny Miami Beach provides the backdrop for the 2007 Palisade User Conference North America on October 25 and 26. The event will feature keynote speaker Dr. Wayne Winston, as well as a cadre of risk professionals and luminaries from around the world.
:: World Class Setting, World Class Delegates
Hosted at the Alexander All-Suite Oceanfront Resort, this year’s venue is located on Millionaire’s Row and is only minutes from South Beach, Bal Harbour, and the Art Deco district. The hotel’s elegant meeting space and setting act as an ideal complement to this two-day risk and decision analysis forum.
Experience real-world case studies from industry experts, hands-on software training, and best practice sessions. Rub elbows with top level consultants and industry leaders from across the spectrum of business and research. Register now for the special early-bird rate of only $295 – that’s $200 off the regular price. Book your room at the Alexander now and enjoy the special conference rate of only $199 per night – over 35% off the regular rate! Call the Alexander at 800-327-6121 or
e-mail your request, and be sure to mention the Palisade User Conference.
:: Keynote: Dr. Wayne Winston
Palisade is delighted to introduce Dr. Winston as keynote speaker. Dr. Winston is a professor in the Operations and Decision Technologies department at the Kelley School of Business at Indiana University in Bloomington. He has been teaching for thirty years, and consistently receives national recognition for excellence in business education. He specializes in spreadsheet modeling and DecisionTools Suite software applied to operations research. The author of several books, Dr. Winston regularly teaches Excel to Microsoft staff, and is a highly-regarded consultant for Fortune 500 outside of the academic community. He has degrees from MIT and Yale.
:: Why Attend?
:: Meet Palisade Engineers
Palisade’s top software engineers will be on-hand for exciting roundtable discussions. You’ll be able to provide feedback about Palisade tools and seek advice for your particular modeling issues. So bring your wish list and get to know the people behind @RISK, the DecisionTools Suite, and NeuralTools.
Ask Amy continued from above
“Multicollinearity” is defined as “the presence of a fairly strong linear relationship between two or more explanatory variables”, and it can make estimation difficult. Consider the following example. It is a very simple example, but it definitely serves the purpose of demonstrating the warnings of and how to deal with and recognize multicollinearity.