for modeling Energy Policies
Students at Columbia University’s School of International & Public Affairs (SIPA) learn to deal with risk on a global level, and in Professor Roy Nersesian’s Quantitative Methods in Energy and Policy Analysis course they gain hands-on experience in the development and interpretation of quantitative models for project evaluation and policy assessment. The students develop cash flow and market models using Palisade’s @RISK.
:: Regional Seminars
Introductory and Intermediate Risk and Decision Assessment
Feb. 20-21, Toronto, ON
Feb. 27-28, Orlando, FL
April 3-4, San Juan, PR
Risk and Decision Assessment Training with an Introduction to Insurance Applications
Feb. 6-7, Hamilton, Bermuda
Evaluación de riesgo para usuarios principiantes / intermedios (3 días)
Del 21 al 23 de febrero
Distrito Federal, México
:: Live Web Training
Introduction to Risk and Decision Assessment Training Part I
Feb. 13-14
March 9-10
Introduction to Risk and Decision Assessment Training Part II
Feb. 9-10
March 2-3
Expert Answers to
Technical Questions
Dear Amy,
I have a rather large model with thousands of inputs that spans multiple worksheets. I love @RISK’s unlimited capacity, but is there any way I can speed up simulation time?
- P.M., Bend, Oregon
Dear P.M.,As you know, @RISK can tackle any size model you give it. There are a number of ways to reduce simulation run-time. In your Simulation Settings dialog, there are a variety of options that affect simulation speed. Make sure the Update Display option is not checked, so the computations are not made on-screen during the simulation. Similarly, do not check the Update Real Time for your @RISK Results Window option, so graphs and tables don’t update during the simulation...
Case Study:
NeuralTools and StatTools Predict Hospital Patient Load
Healthcare industry consultant Barbara Tawney needed to forecast patient loads for the entire metropolitan hospital system of Richmond, Virginia. But unpredictable patient demand had resulted in two occasions when all nine hospitals in the system reached capacity and patients had to be diverted to healthcare facilities outside the area. To figure out how to anticipate for surges in patient load, Tawney turned to Palisade’s StatTools® and NeuralTools® data analysis products. With the cooperation of Virginia Health Information (VHI), a non-profit organization that collects and archives all the healthcare data statewide, she was granted limited access to metropolitan Richmond patient data for the four years from 2000 to 2003. Time series data were derived from hospital billing information for about 600,000 patients being treated at area hospitals during 2000-2003. The patient level data (PLD) were detailed in 78 different fields, including dates of admission and discharge, diagnosis, and length of stay.
:: StatTools for Autocorrelation
According to Tawney, “I was looking for a user-friendly way to do autocorrelation, and a colleague recommended StatTools to me.” She created time series for the data by “binning” the PLD according to the dates and times of activity for each case. The time series data were analyzed for daily, weekly and event trends, and Tawney reported “StatTools did what I needed without the time and expense of a heavy-duty stats package.”
:: NeuralTools Manages Patient Load
Next, it was time for Tawney to predict future patient loads using NeuralTools. After first training NeuralTools on a subset of the data, she analyzed the entire dataset. Tawney determined that patient load peaked at mid-week during most weeks of the year. Holiday periods also have a different, distinctive pattern. The number of patients entering the hospitals just before major holidays was lower than normal but was followed on Monday by an influx of patients that stretched the facility’s resources. Now, being able to predict patient load allows for more efficient allocation of resources and better staff scheduling.
read the case study
learn more about NeuralTools
Industry Application:
Reinsurance and @RISK
Insuring most of the major insurance companies in the world against catastrophic losses is no small undertaking. In the reinsurance industry, calculating how to balance billions of dollars in potential losses against premiums is a high-wire exercise with high-stakes. @RISK is used by a reinsurance firms to model exposure to risk and potential liabilities in order to establish premiums. The insurance companies who are clients of reinsurers are exposed to any number of different types of risk, which means that reinsurance companies have to think of their own exposure to risk in terms of clusters of liability. This makes for pretty complex contract structures and very large transactions worth many millions. In addition they must take into account premium adjustment, loss distributions, and of course, profit. Often the transactions reinsurance companies must contemplate are too complex to fit into other decision support tools. But Palisade’s reinsurance customers have found that @RISK can be used to effectively model these transactions and arrive at the most accurate outcome distributions possible.
Renaissance Re uses @RISK
learn more about @RISK
Product Spotlight:
DecisionTools Suite – PrecisionTree
:: Decision Analysis in Excel
PrecisionTree is the decision analysis add-in for Excel that lets you illustrate to others what you should do and why. Available as part of the DecisionTools Suite or by itself, PrecisionTree can create decision trees in your spreadsheets. Use decision trees to visually model a sequence of decision-making events. Results include a full statistical report, sensitivity charts and risk profile graphs.
PrecisionTree offers point-and-click simplicity when constructing your decision tree. Trees are built directly in your spreadsheet, so you can enter values directly into cells. PrecisionTree’s unique interface makes it a standout among decision analysis packages.
:: Influence Diagrams for General Structure
Influence diagrams are a particularly interesting feature of PrecisionTree. Unlike decision trees, influence diagrams are not sequential in nature. Rather, they are a graphical way to depict the relationships between different events of a complex decision. Influence diagrams are a great way to map out the general structure of a decision model. You can see model results without converting your influence diagram to a decision tree. Or, have PrecisionTree automatically build a decision tree for you from your influence diagram.
With PrecisionTree, you’ll be making better decisions – and communicating your logic to others – in no time.
“PrecisionTree's attraction is its capacity to value complex decisions, which often involve multiple, sequential decision steps. We considered using financial option calculators to analyze the real options that are embedded in our complex decisions, but we found that they simply can't solve for the real option value in projects with multiple, sequential investment decisions. Decision trees are really the only tool that can correctly value multiple sequential decisions where uncertainty is private risk. PrecisionTree has been very useful in helping us break complex projects down into individual decision options, helping us understand the uncertainties, and ultimately helping us make superior decisions.”
- Bob Hunt, Procter & Gamble
learn more about PrecisionTree
Columbia University Uses @RISK continued from above :: A Sure Thing? Roy Nersesian is the author of several books on finance and risk analysis available through Palisade. In conclusion he states “I don’t see how a manager can be effective without considering the risks inherent in any business decision. In other words, I don’t know how they live without @RISK.”
:: @RISK Provides More Complete Picture
According to Professor Nersesian, “We start by building a static model, and not surprisingly, the results look great. Then we add risk into the model using @RISK for a proper risk analysis, and the picture changes. The students quickly learn that there are possible negative outcomes.”
The case for risk analysis and risk management is pretty compelling. One example used in the course is a financial analysis of an oil production project in a developing nation. A static model suggests that the project is a slam dunk. However when uncertain factors such as future oil prices and interest rates are added using @RISK, the model becomes much more interesting. The students learn how the impact of variables such as the global price of oil and lending rates can turn a sure thing into a fiasco. The lesson is to identify risks, understand their impact through modeling, and then implement appropriate changes to the structure of the financing to mitigate risk.
Ask Amy continued from above
...You can also check None under the Collect Distribution Samples section, so you are not collecting data for your inputs, just your output. In addition, you can choose to Minimize @RISK and Excel during the simulation, so you can do other things.
If you are running @RISK Industrial, you can run your simulations using multiple CPUs in a single machine by checking the Use Multiple CPUs option in Simulation Settings. You can also purchase @RISKAccelerator separately to run simulations over multiple CPUs on a network. Finally, you can often add additional RAM to your computer very cheaply, which speeds up simulations.
E-mail comments or suggestions to: sales@palisade.com
©2006 Palisade Corporation, 798 Cascadilla Street, Ithaca, NY 14850 USA
$unsub