Microsoft Excel statistics have a plethora of uses, limited only by the analyst's imagination, data, and job description. What are these uses and how do you choose the right Excel toolset for maximum utility?

Let's say you work at BP and you're interested in the relationship between the depth of oil wells in the Caribbean with the frequency of oil rig problems. You have several thousand monthly data points of disaster event frequency data and the average depth of each well from the ocean surface to the sea floor, and from the sea floor to the oil pool. You need to quickly generate a probability distribution and estimates of the likelihood of future oil rig disaster events for a board meeting in 1 hour. Several Microsoft Excel statistics tools can generate this analysis in 15 minutes or less. Too bad BP didn't know!

Another example: You hold a portfolio of corporate bonds rated triple-A, Baa, and C in a customer account which has generated significant paper profits in the last year. Your customer asks you whether he should sell this portfolio, or whether he should hold it and buy protection with credit derivatives, and needs to know the answer by the end of the day. You have access to extensive data on historical default probabilities of different bonds with different ratings, as well as historical time series of credit spreads, CDS prices, and equity prices. Using this data and a Microsoft Excel statistics library, you are able to answer with 95% confidence, that based on current market conditions, the length of the bond price runup, and the current economic cycle, credit default spreads on speculative grade bonds are likely to increase by at least 15% in the next 6 months. You recommend selling the C-rated bonds, buying index CDS on the High Yield index, reducing the portfolio's Baa exposure gradually, and holding the triple-A rated bonds.

A final example might be cyclical long term weather patterns to project the price of a basket of food commodities including wheat, corn, beef, soybeans, and orange juice. By importing national weather pattern data from different geographic locations and inflation-adjusted commodity prices into Excel and running a multivariate regression analysis, you are able to ascertain the predictive quality of weather on commodity prices during different time periods. By comparing these results with a similar exercise using geographic population density, lifespan, and education levels to predict commodity prices, you deduce a further potential relationship. Such complex analyses can be easily computed using Excel and statistical tools.

As shown by these examples, the uses of Microsoft Excel statistics capabilities are never-ending.