Professional Employment Opportunity:
:: Technical Trainer/Consultant
Palisade Corporation is looking for a talented Technical Trainer/Consultant to conduct hands-on software training for our clients. Located in Ithaca, New York, in the heart of the Finger Lakes Region, Palisade employees enjoy a beautiful area, a low cost of living, and a challenging yet relaxed work environment. Ithaca is the home of Cornell University and Ithaca College, and offers big-city cultural and entertainment options, in a smaller town setting - a great place to start or continue your career.

learn more about Palisade, as well as this and other positions

Case Study:
A Butterfly Flaps Its Wings . . .
Managing agricultural crop pests is a complex, moving-target type of challenge for farmers and biologists. One tactic often employed is biological control, or releasing good bugs to eat bad bugs that damage crops. However, sometimes the good bugs eat other good bugs, which may create other problems.

:: @RISK Weighs Good Bugs and Bad Bug
Working with a team of researchers, Robert L. Koch, Ph.D., Department of Entomology, University of Minnesota, developed a quantitative risk assessment model using @RISK to better understand the potential impact of the multi-colored Asian lady beetle - originally intended to combat crop-eating aphids - on monarch butterflies. The butterflies became unwitting fodder for the lady beetle when the aphid population fell. This assessment considered a potential worst-case scenario for the impact of the lady beetle on monarch butterflies, and @RISK was used to characterize the distributions of the measures of exposure.

:: Modeling Butterfly Population
To incorporate uncertainty into the model, Koch used @RISK to model the probability distribution of outcomes by sampling exposure values for each input variable from their own respective probability distributions. Such input variables included habitat productivity (egg density of monarch butterfly by area, crop, and lady beetle density), exposure assessment (quantity, proximity, and time of lady beetle exposure to immature monarch stages), and effect assessment (predation of lady beetle on immature monarch stages and aphid densities). He then calculated the model outcomes through 100,000 iterations with Latin hypercube sampling. Probability distributions for variables in the model were obtained by fitting theoretical distributions to observed data using Palisade's BestFit and @RISK.

To determine the relative importance of each input variable in the model and the sensitivity of the model to small changes of these variables, @RISK provided a way to conduct multivariate stepwise regression, a statistical regression technique that ranks the order of impact that each input has on the bottom line. Results of these analyses were then displayed in tornado graphs indicating standard deviations in relative productivity changes. The order of impact of the different developmental stages of the lady beetle on the different life stages of the monarch butterfly could then be better assessed.

:: Key Risks Revealed
In this case, Koch's @RISK model assessment demonstrates that the multi-colored Asian lady beetle has a 42.78% potential for killing all instances of third developmental stage monarch butterflies under certain conditions. More importantly, however, this research highlights the importance of exposure analysis in estimating overall risk. In particular, exposure and subsequent risk varied greatly between corn and soybean cropping systems. This risk assessment may be used as a model for future assessments incorporating additional habitats and other influential factors.

read the full research paper
read other case studies
read other case articles

Product Spotlight:
BestFit: Fit Your Data to the Best Distribution... in Seconds!
:: Decision Analysis in Excel
BestFit finds the distribution that best fits your data. Simply import your data set into BestFit and click the Run Fit button. BestFit tests up to 27 different distribution types to find the best fit for your data. You can display results as presentation-quality graphs, or generate a full statistical report. Automatic goodness of fit testing will show you at a glance the accuracy of BestFit's answers. BestFit 4.5 is available as a stand-alone program or fully integrated with every copy of @RISK 4.5 Professional and Industrial, the risk analysis and simulation add-in for Excel.

:: So why fit distributions to data?
Because if you don't (or if you select the wrong distribution), any analysis you run could have serious errors that can cost you time and money. If your data was generated by a random process, you'll get the best modeling results possible by accurately describing that process. And the best way to do that is with a fitted probability distribution. BestFit's goal is to find the distribution that best fits your input data. BestFit does not produce an absolute answer; it identifies a distribution that most likely produced your data.

:: Who should use BestFit?
Anyone who works with data can use BestFit. Apply it to business situations such as actuarial or claims adjustment, or to science and engineering problems such as oil well drilling or time between events. You can import data from your spreadsheet and export the results as graphic files to your report or presentation.

:: BestFit Features: