Sep 2018 - May 2020
A core module of the Oxford EMBA, Analytics is taught throughout the first weeks of the programme, and covers a number of areas.
Firstly, it covers general statistics, providing a recap of general and inferential statistics, and ensuring that students know their way around key mathematical techniques and concepts. Secondly, the module covers Decision Analysis, which is a collection of methods to structure decisions in a quantitative manner. Decision Analysis is mostly done with the aid of software add-ons allowing to automatically draw and calculate Decision Trees, greatly enhancing the ability to calculate probabilities for complex decision models, and ensuring a fair amount of “fun” as seeing decision trees auto-calculate probabilities is highly satisfactory. Thirdly, the course covers Risk Analysis, and in particular Monte Carlo simulation, allowing students to build and run their own models, again to great satisfaction when the simulation works correctly and results can be analyzed in depth. Fourthly, the module covers Regression, namely a collection of methods aimed at determining the equation best describing a set of data points.
What makes the Analytics module so useful is that what is taught can be directly translated back into the workplace. Statistical concepts such as normal distributions are used in engineering to analyze deviances from baseline operating numbers; the entire field of Six Sigma is built on the concept of normal distribution. Decision Analysis is used, but likely should be used more, in project planning, where multiple options with associated odds are evaluated to determine the best course of action. Risk Analysis and Monte Carlo simulation are widely used when performing analysis on price movements of financial instruments. Finally, regression is used in forecasting weather patterns, by building a model based on previous weather data points that can be then used to forecast future weather patterns.
From my perspective, the Analytics module was particularly enjoyable. First, because some of the concepts covered were quite complex, students collaborated a lot, explaining to each other how to tackle specific problems, and in doing so got to know each other better. Second, the course was taught at a pace that allowed those already having experience in the subject to learn more advanced concepts, whilst ensuring that those who had not engaged with analytics before had enough time to absorb new ideas and ponder things through. Third, many examples were provided to bring concepts back to reality; for example, we learnt that decision trees are the basis of driverless cars, and that global warming forecasts use regression techniques to determine scenarios for future years. Last, the course made extensive use of spreadsheets, and it was fun to see Mac users attempting to work through decision trees using the Mac spreadsheet software.Back to top of article